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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    多
    -0.08
     test
    -0.07
    	scanf
    -0.07
    owania
    -0.07
     phi
    -0.07
    mid
    -0.07
    مين
    -0.07
    scanf
    -0.07
     node
    -0.07
     nel
    -0.06
    POSITIVE LOGITS
     helicopt
    0.07
    ipzig
    0.07
     hates
    0.07
    伊利
    0.07
     Contractors
    0.07
    IID
    0.07
    웽
    0.06
    爱心
    0.06
    ":[{"
    0.06
    Collider
    0.06
    Act Density 0.054%

    No Known Activations