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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     len
    -0.07
     invade
    -0.06
    头
    -0.06
    cko
    -0.06
    Failed
    -0.06
    ț
    -0.05
    聽
    -0.05
    泰
    -0.05
     rollback
    -0.05
     senha
    -0.05
    POSITIVE LOGITS
     Butt
    0.07
     활
    0.07
     زند
    0.07
     grenade
    0.06
     organisers
    0.06
     司
    0.06
    picked
    0.06
    .setToolTip
    0.06
     FAMILY
    0.06
    司
    0.06
    Act Density 0.126%

    No Known Activations