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

    Neuronpedia

    INDEX
    Explanations

    modern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Weight
    -0.07
     Messages
    -0.07
    packed
    -0.07
     accept
    -0.07
    lık
    -0.07
    _chg
    -0.06
     tanın
    -0.06
     Handle
    -0.06
    tooltip
    -0.06
    살
    -0.06
    POSITIVE LOGITS
    modern
    0.08
     necessary
    0.06
     Balt
    0.06
    "]
↵
    0.06
    _FRE
    0.06
     carniv
    0.06
    ductory
    0.06
    .nanoTime
    0.06
     уров
    0.06
     woke
    0.06
    Act Density 0.005%

    No Known Activations