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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    兄
    -0.08
    𪩘
    -0.07
    _MAXIMUM
    -0.07
    𬃊
    -0.07
     thereafter
    -0.07
    Mensaje
    -0.07
    criptions
    -0.06
    difference
    -0.06
    מדובר
    -0.06
    呢
    -0.06
    POSITIVE LOGITS
     Pants
    0.09
     Potential
    0.08
    _PUT
    0.07
    Polit
    0.07
    refixer
    0.07
     Lily
    0.07
    }());↵
    0.07
     الوطني
    0.07
    卟
    0.07
    _strike
    0.06
    Act Density 0.006%

    No Known Activations