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

    Neuronpedia

    INDEX
    Explanations

    actual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ollapse
    -0.07
     जनवर
    -0.06
    ographics
    -0.06
    .lib
    -0.06
     får
    -0.06
    reater
    -0.06
    _ALIAS
    -0.06
     continually
    -0.05
     Fern
    -0.05
    公
    -0.05
    POSITIVE LOGITS
    €↵
    0.07
    люд
    0.06
    Hotel
    0.06
     ErrorCode
    0.06
     інших
    0.06
    Bron
    0.06
    .Decode
    0.06
     protestors
    0.06
    $search
    0.06
     ginger
    0.06
    Act Density 0.000%

    No Known Activations