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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ration
    -0.07
    ForObject
    -0.06
    ーレ
    -0.06
    �
    -0.06
    _get
    -0.06
     Gur
    -0.06
     Sanct
    -0.06
     finns
    -0.06
    雪
    -0.06
    SPATH
    -0.06
    POSITIVE LOGITS
     بق
    0.07
     �
    0.07
    imageView
    0.07
     bigotry
    0.06
    _combo
    0.06
     tat
    0.06
    .InnerException
    0.06
    _hd
    0.06
    248
    0.06
    .roles
    0.06
    Act Density 0.000%

    No Known Activations