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
    🍦
    -0.07
    ﴩ
    -0.07
     thắ
    -0.07
    밞
    -0.07
    �
    -0.07
    mit
    -0.06
    前瞻性
    -0.06
    
    -0.06
    .’”↵↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Leisure
    0.07
    archs
    0.07
    illum
    0.07
     دون
    0.07
     adulti
    0.07
     цен
    0.07
     Creature
    0.07
    lections
    0.07
    _entities
    0.07
    فشل
    0.07
    Act Density 0.001%

    No Known Activations