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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _else
    -0.07
     brokerage
    -0.07
    +S
    -0.06
     rubble
    -0.06
    .after
    -0.06
    Except
    -0.06
    .",
    -0.06
     shin
    -0.06
     timeout
    -0.06
    -прав
    -0.06
    POSITIVE LOGITS
    GF
    0.07
    _SS
    0.06
    ::::::::::::::::
    0.06
    Chef
    0.06
     grinding
    0.06
    .Canvas
    0.06
     INITIAL
    0.06
    DialogContent
    0.06
     pairing
    0.06
    tensor
    0.06
    Act Density 0.057%

    No Known Activations