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

    Neuronpedia

    INDEX
    Explanations

    basic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boilers
    -0.07
    терн
    -0.07
    iltere
    -0.06
     Loren
    -0.06
    فش
    -0.06
    層
    -0.06
     мар
    -0.06
    Drawing
    -0.06
     бо
    -0.06
    uelles
    -0.06
    POSITIVE LOGITS
    (Environment
    0.07
     ‐
    0.06
     kosher
    0.06
     �
    0.06
     チ
    0.06
     sebagai
    0.06
     estas
    0.06
    timestamps
    0.06
     bingo
    0.06
    IMARY
    0.06
    Act Density 0.002%

    No Known Activations