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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Davies
    -0.06
    _events
    -0.06
    (real
    -0.06
     Err
    -0.06
    ceptor
    -0.06
    chandle
    -0.06
    (),
    -0.06
    (power
    -0.06
    (ID
    -0.06
     distributions
    -0.06
    POSITIVE LOGITS
     soph
    0.06
     akin
    0.06
    READING
    0.06
     село
    0.06
     duly
    0.06
     хви
    0.06
    -Identifier
    0.06
    igmat
    0.06
     whisper
    0.06
     kabil
    0.06
    Act Density 0.082%

    No Known Activations