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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bells
    -0.06
     paranoia
    -0.06
    Foo
    -0.06
     distractions
    -0.06
     �
    -0.06
     leggings
    -0.06
    .items
    -0.06
    _FAILED
    -0.06
     Hmm
    -0.06
    eat
    -0.06
    POSITIVE LOGITS
    CGSize
    0.08
    .Location
    0.07
     discre
    0.06
    ờ
    0.06
    -degree
    0.06
     Основ
    0.06
     nghị
    0.06
     каль
    0.06
    ολ
    0.06
    一次
    0.06
    Act Density 0.004%

    No Known Activations