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

    Neuronpedia

    INDEX
    Explanations

    Software alternatives/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AIS
    -0.06
     BOOT
    -0.06
    ());
↵
    -0.06
    等
    -0.06
    cdr
    -0.06
     बज
    -0.06
    (/
    -0.06
    spark
    -0.05
     Corps
    -0.05
    ).↵↵
    -0.05
    POSITIVE LOGITS
    (Code
    0.07
    VE
    0.07
    ificial
    0.07
     Gam
    0.07
    _FE
    0.07
    де
    0.07
    HEN
    0.07
    mma
    0.06
     сто
    0.06
    igham
    0.06
    Act Density 0.000%

    No Known Activations