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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _department
    -0.08
    =email
    -0.07
    CLA
    -0.07
     collect
    -0.07
    DOC
    -0.07
     אלק
    -0.07
    _bio
    -0.07
    .AUTO
    -0.07
    _categoria
    -0.07
    𝒜
    -0.06
    POSITIVE LOGITS
    乱象
    0.07
    [String
    0.07
    errick
    0.07
     существ
    0.07
     multi
    0.07
    山路
    0.07
     timespec
    0.07
    (kernel
    0.07
    ramids
    0.07
    铺
    0.07
    Act Density 0.005%

    No Known Activations