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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trees
    -0.07
     landlords
    -0.07
    _hex
    -0.07
     sesame
    -0.07
     hunters
    -0.07
    .dim
    -0.07
     orphan
    -0.06
    社會
    -0.06
    $title
    -0.06
     mohli
    -0.06
    POSITIVE LOGITS
    Integrated
    0.08
     Integrated
    0.07
     아주
    0.06
    _MetadataUsageId
    0.06
    fastcall
    0.06
    _wf
    0.06
    _display
    0.06
     Sask
    0.06
    UseProgram
    0.06
    ()==
    0.06
    Act Density 0.028%

    No Known Activations