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

    Neuronpedia

    INDEX
    Explanations

    math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     人
    -0.07
    _SEQ
    -0.07
    pst
    -0.07
    ,buf
    -0.06
     Gu
    -0.06
     至
    -0.06
    }:
    -0.06
     Prevent
    -0.06
    ocha
    -0.06
    Cnt
    -0.06
    POSITIVE LOGITS
    iswa
    0.06
    female
    0.06
    mental
    0.06
     Стар
    0.06
    änner
    0.06
     hic
    0.06
     annoyance
    0.06
    Warning
    0.06
     nir
    0.06
    dress
    0.06
    Act Density 0.008%

    No Known Activations