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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oten
    -0.09
    账号
    -0.08
    JSONArray
    -0.07
     steward
    -0.07
     manten
    -0.07
    Ꮥ
    -0.07
    .zoom
    -0.07
    Aff
    -0.07
     mutil
    -0.07
    .MouseEvent
    -0.07
    POSITIVE LOGITS
    0.09
    기
    0.08
     Grund
    0.07
     �
    0.07
    0.07
    不是
    0.06
    应力
    0.06
     grandi
    0.06
    3
    0.06
     tricks
    0.06
    Act Density 0.017%

    No Known Activations