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

    Neuronpedia

    INDEX
    Explanations

    Blog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слишком
    -0.07
     součást
    -0.07
    atter
    -0.06
    (cube
    -0.06
    _ATTACHMENT
    -0.06
    více
    -0.06
     alc
    -0.06
    _attributes
    -0.06
    paces
    -0.06
    setId
    -0.06
    POSITIVE LOGITS
     가
    0.11
    -gnu
    0.09
    .display
    0.08
    spotify
    0.07
    Argument
    0.07
    */↵↵↵
    0.07
    hide
    0.07
     Poll
    0.06
     Taken
    0.06
     Impossible
    0.06
    Act Density 0.004%

    No Known Activations