Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or contrasts in product features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before a number or percentage

    np_acts-logits-general · gemini-2.0-flash

    symbols followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.57
    DOCTYPE
    -0.55
    pence
    -0.55
    HSSF
    -0.54
    ThroughAttribute
    -0.53
    apimachinery
    -0.52
     nawr
    -0.51
    EntityType
    -0.51
     TypeError
    -0.50
     mindig
    -0.49
    POSITIVE LOGITS
     unlike
    0.99
    unlike
    0.93
     Compared
    0.93
     compared
    0.91
     Unlike
    0.90
    Compared
    0.89
    Unlike
    0.87
     Weigh
    0.84
    Weigh
    0.82
    Overall
    0.77
    Act Density 0.150%

    No Known Activations