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

    Neuronpedia

    INDEX
    Explanations

    various documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.51
    natured
    -0.46
     وارد
    -0.46
     发表于
    -0.45
    DOCTYPE
    -0.45
    Personensuche
    -0.45
    lidean
    -0.45
    Rüyada
    -0.44
    исленность
    -0.43
     amp
    -0.43
    POSITIVE LOGITS
    GHIJKLM
    0.55
     Daily
    0.55
    \{\\
    0.54
     Altern
    0.54
     الحره
    0.53
     renseignements
    0.53
    OGND
    0.52
    Primitives
    0.52
     Spitfire
    0.52
    oxia
    0.51
    Act Density 0.000%

    No Known Activations