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

    Neuronpedia

    INDEX
    Explanations

    Quotation/parenthesis marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thief
    -0.07
     Susp
    -0.07
    .lua
    -0.07
    editor
    -0.06
    ("\\
    -0.06
     western
    -0.06
     کارت
    -0.06
    แส
    -0.06
     squad
    -0.06
    는다
    -0.06
    POSITIVE LOGITS
    �
    0.07
    款
    0.06
    ываем
    0.06
    cia
    0.06
    报名
    0.06
    dives
    0.06
     impacts
    0.06
    기준
    0.06
    agu
    0.06
     INST
    0.06
    Act Density 0.015%

    No Known Activations