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

    Neuronpedia

    INDEX
    Explanations

    Rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reasoned
    -0.07
    に基づ
    -0.07
    _STATUS
    -0.07
    ܢ
    -0.07
    פד
    -0.07
     Федер
    -0.07
    _re
    -0.07
    ᨨ
    -0.07
    ']],
    -0.06
    _cmp
    -0.06
    POSITIVE LOGITS
     тест
    0.06
     forgotten
    0.06
     myself
    0.06
     saved
    0.06
     Lost
    0.06
     bigotry
    0.06
    앗
    0.06
     Então
    0.06
    جماهير
    0.06
     Phot
    0.06
    Act Density 0.001%

    No Known Activations