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

    Neuronpedia

    INDEX
    Explanations

    distributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parsers
    -0.07
    endale
    -0.06
     Sofa
    -0.06
    arbonate
    -0.06
    CA
    -0.06
    _ter
    -0.06
     kings
    -0.06
    一个人
    -0.06
     battlefield
    -0.06
    Rub
    -0.06
    POSITIVE LOGITS
    _setopt
    0.07
    (gr
    0.06
    @JsonProperty
    0.06
     assortment
    0.06
     titan
    0.06
    랑스
    0.06
    ectar
    0.06
     intval
    0.06
    .environment
    0.06
    .FloatTensor
    0.06
    Act Density 0.003%

    No Known Activations