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
    П
    -0.07
    野
    -0.07
    isk
    -0.06
    FS
    -0.06
    pickle
    -0.06
    ⽔
    -0.06
    -buffer
    -0.06
    淡
    -0.06
    안내
    -0.06
    髓
    -0.06
    POSITIVE LOGITS
    不管你
    0.09
    .devices
    0.07
    olum
    0.07
    repid
    0.07
    #End
    0.06
    UBL
    0.06
    EGA
    0.06
    upro
    0.06
     Thin
    0.06
     Gunn
    0.06
    Act Density 0.074%

    No Known Activations