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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Execute
    -0.07
    Behaviour
    -0.07
    θεί
    -0.07
    慧
    -0.06
    dık
    -0.06
     Hussein
    -0.06
    Grammar
    -0.06
    紹
    -0.06
    \Eloquent
    -0.06
     признач
    -0.05
    POSITIVE LOGITS
     repealed
    0.07
    ifle
    0.07
    ».
    0.06
     Phương
    0.06
    逆
    0.06
     shook
    0.06
    )).↵
    0.06
    (cm
    0.06
     Igor
    0.06
     recommended
    0.06
    Act Density 0.003%

    No Known Activations