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

    Neuronpedia

    INDEX
    Explanations

    Jewish topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (timer
    -0.07
    анія
    -0.06
     ayrı
    -0.06
    _mtime
    -0.06
    -player
    -0.06
    -pound
    -0.06
     DateFormat
    -0.06
    _creation
    -0.06
    끔
    -0.06
    early
    -0.06
    POSITIVE LOGITS
     Antony
    0.07
    ¢
    0.07
    .dx
    0.06
    .Job
    0.06
    ,len
    0.06
    oly
    0.06
    .MOD
    0.06
    clo
    0.06
    proj
    0.06
     øns
    0.06
    Act Density 0.011%

    No Known Activations