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

    Neuronpedia

    INDEX
    Explanations

    say link

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فهرست
    -0.07
     twelve
    -0.07
     earnest
    -0.07
     drunken
    -0.07
     было
    -0.06
     küçük
    -0.06
    された
    -0.06
    Prefix
    -0.06
     büyük
    -0.06
    енных
    -0.06
    POSITIVE LOGITS
     RPC
    0.07
     initWithTitle
    0.06
     spécial
    0.06
    .getBounds
    0.06
     //↵↵
    0.06
     EPA
    0.06
     Німеч
    0.06
    ummies
    0.06
    _RED
    0.05
    ...)
    0.05
    Act Density 0.073%

    No Known Activations