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

    Neuronpedia

    INDEX
    Explanations

    contractions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ℝ
    0.33
     זו
    0.32
     ある
    0.32
     ”
    0.31
     issn
    0.31
     ima
    0.31
     Apr
    0.31
     を
    0.31
     MFA
    0.30
     yamaha
    0.30
    POSITIVE LOGITS
    Judging
    0.37
    Compared
    0.35
    Unlike
    0.34
    Due
    0.33
    Because
    0.32
    While
    0.32
    Founded
    0.31
    Needless
    0.30
    unlike
    0.29
    Fans
    0.29
    Act Density 0.150%

    No Known Activations