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

    Neuronpedia

    INDEX
    Explanations

    replies and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Step
    0.44
    mRNA
    0.40
     дове
    0.36
     spoke
    0.36
     unlocks
    0.36
    Error
    0.35
    GP
    0.35
    Gal
    0.35
     Exponential
    0.35
    Weber
    0.35
    POSITIVE LOGITS
     reply
    0.48
     Replies
    0.46
     comment
    0.46
     Reply
    0.46
     COMMENT
    0.43
     comentário
    0.43
    ঠা
    0.42
     REPLY
    0.42
    reply
    0.42
    コメント
    0.41
    Act Density 0.000%

    No Known Activations