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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ประว
    -0.08
    Warn
    -0.07
     Ziel
    -0.07
    �
    -0.06
     Moy
    -0.06
     Registr
    -0.06
    ventional
    -0.06
     streak
    -0.06
    (rule
    -0.06
     vyvol
    -0.06
    POSITIVE LOGITS
     hoş
    0.07
     şu
    0.07
     olmayan
    0.06
     Через
    0.06
    -chan
    0.06
    &r
    0.06
    、​
    0.06
    ?>/
    0.06
    _fixed
    0.06
     bure
    0.06
    Act Density 0.016%

    No Known Activations