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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chine
    -0.07
    -free
    -0.07
     ext
    -0.07
    Answer
    -0.07
     verze
    -0.06
     Engineering
    -0.06
    claration
    -0.06
    _eps
    -0.06
     |↵
    -0.06
     підприємства
    -0.06
    POSITIVE LOGITS
    oft
    0.07
    tiny
    0.07
    .sprites
    0.07
    _STANDARD
    0.06
    forward
    0.06
     Skinny
    0.06
     gib
    0.06
    (TokenType
    0.06
    seeing
    0.06
     (~
    0.06
    Act Density 0.048%

    No Known Activations