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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peed
    -0.07
     Vul
    -0.07
    쩃
    -0.07
     Jews
    -0.07
    vr
    -0.07
    abd
    -0.07
     reconnaissance
    -0.06
    rious
    -0.06
    حت
    -0.06
    joined
    -0.06
    POSITIVE LOGITS
    ESTAMP
    0.08
    Ò
    0.07
    -interface
    0.07
    プロジェクト
    0.07
     pixmap
    0.07
    <M
    0.07
     &$
    0.07
     Stück
    0.07
     제품
    0.07
     חושב
    0.07
    Act Density 0.000%

    No Known Activations