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

    Neuronpedia

    INDEX
    Explanations

    sophisticated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    だけど
    -0.07
    .mount
    -0.06
     airspace
    -0.06
     mountains
    -0.06
     Raiders
    -0.06
     flavour
    -0.06
    .Sample
    -0.06
     NSMutableArray
    -0.06
    aniel
    -0.06
     meats
    -0.06
    POSITIVE LOGITS
    Blake
    0.07
    lfw
    0.06
     ###↵
    0.06
     jó
    0.06
    ounded
    0.06
    -sign
    0.06
     Von
    0.06
     '-';↵
    0.06
    dü
    0.06
    izz
    0.06
    Act Density 0.000%

    No Known Activations