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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating representation or significance of concepts and values

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

    indicates something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ellos
    -0.36
     podamos
    -0.34
     позже
    -0.32
    SEGUIR
    -0.32
     jų
    -0.32
    tagHelperRunner
    -0.32
    Faster
    -0.32
     prêtre
    -0.32
     réglable
    -0.32
     google
    -0.31
    POSITIVE LOGITS
     represents
    0.97
    Represents
    0.89
    represents
    0.89
     represent
    0.85
     Represents
    0.82
     REPRESENT
    0.78
     representing
    0.77
     representar
    0.75
     Represent
    0.75
    represent
    0.75
    Act Density 0.037%

    No Known Activations