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

    Neuronpedia

    INDEX
    Explanations

    Center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -track
    -0.07
    rophic
    -0.07
    ipop
    -0.07
    Ḫ
    -0.07
    rij
    -0.07
    ivement
    -0.06
     ea
    -0.06
     Tea
    -0.06
     thighs
    -0.06
    年夜
    -0.06
    POSITIVE LOGITS
    Center
    0.07
    synthesize
    0.07
    .debug
    0.07
    Smart
    0.07
    结尾
    0.07
    _limit
    0.07
     sorter
    0.07
    心理
    0.07
    apper
    0.07
     Mandal
    0.07
    Act Density 0.025%

    No Known Activations