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

    Neuronpedia

    INDEX
    Explanations

    ADC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    redits
    -0.08
     Plane
    -0.08
      
    -0.07
    zee
    -0.07
    .Pr
    -0.07
    umbnails
    -0.07
    ﺔ
    -0.07
    床上
    -0.07
     defs
    -0.07
    Ye
    -0.07
    POSITIVE LOGITS
    भ
    0.07
     tamanho
    0.07
     witch
    0.06
    曾
    0.06
     ***↵
    0.06
     dos
    0.06
    @Configuration
    0.06
    したら
    0.06
    콜
    0.06
    והר
    0.06
    Act Density 0.003%

    No Known Activations