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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mi
    -0.07
     Viol
    -0.07
     gamm
    -0.07
     Meet
    -0.07
    .Doc
    -0.07
     Ellen
    -0.06
    alie
    -0.06
    adder
    -0.06
     hydrogen
    -0.06
    <D
    -0.06
    POSITIVE LOGITS
     htmlentities
    0.08
    哳
    0.07
    บรรยากาศ
    0.07
    >(()
    0.07
    핚
    0.07
     thói
    0.07
    玛
    0.07
    %'
    0.07
     shelf
    0.07
    他
    0.06
    Act Density 0.059%

    No Known Activations