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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fry
    -0.06
    Obama
    -0.06
     pap
    -0.06
     donors
    -0.06
    angers
    -0.06
    亡
    -0.06
     Thursday
    -0.06
     Wednesday
    -0.06
     datetime
    -0.06
     FileNotFoundError
    -0.06
    POSITIVE LOGITS
     свій
    0.06
     испыт
    0.06
     سایر
    0.06
    elopment
    0.06
    ________________________________________________________________
    0.06
    =”
    0.06
     ------------------------------------------------------------------------↵
    0.06
    Про
    0.06
    lepší
    0.06
    __;↵
    0.06
    Act Density 0.290%

    No Known Activations