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

    Neuronpedia

    INDEX
    Explanations

    steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linha
    -0.06
    .Com
    -0.06
    .utility
    -0.06
     alarm
    -0.06
    ��
    -0.06
     coward
    -0.06
     brewers
    -0.06
    ันย
    -0.06
     Craw
    -0.06
    .onPause
    -0.06
    POSITIVE LOGITS
    ρε
    0.06
    _correction
    0.06
     bene
    0.06
     circumstance
    0.06
    worksheet
    0.06
    =a
    0.06
    uristic
    0.06
    真是
    0.06
     clearTimeout
    0.06
     pocházet
    0.05
    Act Density 0.011%

    No Known Activations