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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -trained
    -0.07
     Circus
    -0.07
     Biden
    -0.06
     british
    -0.06
    _filtered
    -0.06
     honor
    -0.06
    sticks
    -0.06
    ckeditor
    -0.06
     ACTIONS
    -0.06
     стали
    -0.06
    POSITIVE LOGITS
    (correct
    0.07
    ูล
    0.06
    .curr
    0.06
    овор
    0.06
    ;}
    0.06
     borrower
    0.06
     RedirectTo
    0.06
    Dados
    0.06
    (proxy
    0.06
    DEPEND
    0.06
    Act Density 0.000%

    No Known Activations