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

    Neuronpedia

    INDEX
    Explanations

    VP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SAY
    -0.07
    myModalLabel
    -0.07
    蹭
    -0.07
    andez
    -0.06
    疤痕
    -0.06
     Berg
    -0.06
     Unblock
    -0.06
    把他
    -0.06
    �
    -0.06
     beaches
    -0.06
    POSITIVE LOGITS
    вол
    0.08
    .Vert
    0.07
    꿴
    0.07
    冬奥会
    0.07
     Вы
    0.07
     publicKey
    0.07
     �
    0.07
    渰
    0.07
    structured
    0.07
    delegate
    0.06
    Act Density 0.005%

    No Known Activations