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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deficits
    -0.07
     derece
    -0.06
    غيرة
    -0.06
    lou
    -0.06
    alla
    -0.06
     Weld
    -0.06
    (Screen
    -0.06
    PublicKey
    -0.06
     měla
    -0.06
    ол
    -0.06
    POSITIVE LOGITS
     ]
↵
    0.07
    ctype
    0.07
    ;',↵
    0.07
    iostream
    0.07
    Fld
    0.07
    .genre
    0.07
    ]][
    0.06
     blinking
    0.06
     gegen
    0.06
     Γ
    0.06
    Act Density 0.002%

    No Known Activations