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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubbed
    -0.08
     WHETHER
    -0.06
     мяс
    -0.06
     нарез
    -0.06
     Pou
    -0.06
    Pour
    -0.06
    modo
    -0.06
    人类
    -0.06
     станет
    -0.06
     складі
    -0.06
    POSITIVE LOGITS
     unable
    0.07
    .us
    0.07
    /block
    0.07
    malloc
    0.07
    ffee
    0.07
    .img
    0.07
    prehensive
    0.06
    discover
    0.06
    .inc
    0.06
    FileName
    0.06
    Act Density 0.024%

    No Known Activations