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

    Neuronpedia

    INDEX
    Explanations

    references to characters in a narrative or storyline dynamics

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

    Prepositions before nouns

    np_acts-logits-general · gemini-2.0-flash

    superstition, obsequious, unseen, such

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poichè
    -1.16
     Whilst
    -1.02
     diatas
    -0.98
     didalam
    -0.96
     perchè
    -0.94
    Whilst
    -0.94
    非常的
    -0.81
     disini
    -0.80
     dimana
    -0.79
     hierbei
    -0.79
    POSITIVE LOGITS
     interminable
    0.87
     freilich
    0.86
    ”—
    0.85
    —
    0.85
    —”
    0.84
     incipient
    0.83
     lousy
    0.83
    !—
    0.81
    —“
    0.79
     sundry
    0.79
    Act Density 0.913%

    No Known Activations