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

    Neuronpedia

    INDEX
    Explanations

    web links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heroes
    -0.08
    ΡΙ
    -0.07
    �
    -0.06
     errors
    -0.06
    ترین
    -0.06
    �
    -0.06
     sometime
    -0.06
    ۵۰
    -0.06
    _wp
    -0.06
     환
    -0.06
    POSITIVE LOGITS
    }->
    0.07
    PB
    0.07
     Аз
    0.06
    _aff
    0.06
    AGAIN
    0.06
    ]?.
    0.06
     عقد
    0.06
     Calgary
    0.06
     vrch
    0.06
    _LESS
    0.06
    Act Density 0.141%

    No Known Activations