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

    Neuronpedia

    INDEX
    Explanations

    Opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liberals
    -0.07
     solid
    -0.07
     angled
    -0.07
     aside
    -0.07
     eyebrow
    -0.07
     tours
    -0.06
     иногда
    -0.06
     سلامت
    -0.06
    》，
    -0.06
    Atomic
    -0.06
    POSITIVE LOGITS
    .Ε
    0.06
     Greenwich
    0.06
    해보
    0.06
     overs
    0.06
    허
    0.06
    ‌تر
    0.06
    @Getter
    0.06
     décor
    0.06
    юр
    0.06
     /\.(
    0.06
    Act Density 0.029%

    No Known Activations