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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kein
    -0.07
     could
    -0.07
    perature
    -0.07
    (to
    -0.07
    된
    -0.07
    دن
    -0.07
    'll
    -0.07
     can
    -0.07
    (training
    -0.06
    FFF
    -0.06
    POSITIVE LOGITS
    _include
    0.07
    _pack
    0.06
    CALL
    0.06
    /register
    0.06
    ToSend
    0.06
    (MediaType
    0.06
    _configs
    0.06
     Μη
    0.06
    .exceptions
    0.06
    _PACK
    0.06
    Act Density 1.255%

    No Known Activations