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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .isdigit
    -0.07
    scri
    -0.07
    /fa
    -0.06
    south
    -0.06
    .UTC
    -0.06
     δημο
    -0.06
    elier
    -0.06
     Hoa
    -0.06
    .new
    -0.06
    cancellationToken
    -0.06
    POSITIVE LOGITS
    assembly
    0.07
    재
    0.06
     behaviours
    0.06
     behaviors
    0.06
    .“
    0.06
    emap
    0.06
     unrest
    0.06
     titten
    0.06
    -away
    0.06
    Granted
    0.06
    Act Density 0.011%

    No Known Activations