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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    impan
    -0.07
    γκε
    -0.06
     stringstream
    -0.06
     pix
    -0.06
    erties
    -0.06
     affects
    -0.06
    ло
    -0.06
    حن
    -0.06
    mp
    -0.06
    RITE
    -0.06
    POSITIVE LOGITS
    тами
    0.07
    전에
    0.06
     pretended
    0.06
    トル
    0.06
    vincia
    0.06
    azy
    0.06
     Gamma
    0.06
     obsolete
    0.06
     обращ
    0.06
     perpendicular
    0.06
    Act Density 0.080%

    No Known Activations