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

    Neuronpedia

    INDEX
    Explanations

    concerns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triangle
    -0.07
    classname
    -0.07
     IllegalArgumentException
    -0.06
    ritz
    -0.06
     mük
    -0.06
     fruit
    -0.06
    /cpp
    -0.06
    ullet
    -0.06
    _cuda
    -0.06
     نزدیک
    -0.06
    POSITIVE LOGITS
     concerns
    0.08
     concern
    0.07
     conquered
    0.07
     len
    0.07
    .Azure
    0.07
     соглас
    0.07
    /report
    0.07
    ौक
    0.06
     permanent
    0.06
     asign
    0.06
    Act Density 0.021%

    No Known Activations