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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insulting
    -0.07
    Woman
    -0.06
     Viewer
    -0.06
     sandbox
    -0.06
     rampant
    -0.06
     Admission
    -0.06
     Archive
    -0.05
     naše
    -0.05
     rack
    -0.05
    <object
    -0.05
    POSITIVE LOGITS
    ，最
    0.07
    CGRect
    0.07
     lumber
    0.07
    gran
    0.07
    acht
    0.06
     quần
    0.06
     Twice
    0.06
     extremes
    0.06
    _POST
    0.06
    ocommerce
    0.06
    Act Density 0.010%

    No Known Activations