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

    Neuronpedia

    INDEX
    Explanations

    contains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Estimate
    -0.07
    Apart
    -0.07
    	action
    -0.06
    xde
    -0.06
    Sem
    -0.06
     monday
    -0.06
     计
    -0.06
    Programming
    -0.06
     upd
    -0.06
     Shapes
    -0.06
    POSITIVE LOGITS
    .Claims
    0.07
     принадлеж
    0.07
    /////////////////////////////////////////////////////////////////////////////↵
    0.07
    番組
    0.07
    тож
    0.07
     رمز
    0.07
     committee
    0.06
     里
    0.06
    -bold
    0.06
     Brett
    0.06
    Act Density 0.005%

    No Known Activations