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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     спир
    -0.07
    병
    -0.06
    '.↵↵
    -0.06
     ([]
    -0.06
    _THRESHOLD
    -0.06
    participants
    -0.06
    agascar
    -0.06
     skirt
    -0.06
    >To
    -0.06
    `↵↵
    -0.06
    POSITIVE LOGITS
    /File
    0.07
     })
↵
    0.07
     Ell
    0.06
    .setOn
    0.06
     Honestly
    0.06
     Mick
    0.06
     BTC
    0.06
     muss
    0.06
     Zaman
    0.06
     بسی
    0.06
    Act Density 0.034%

    No Known Activations