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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     E
    -0.08
    ۇ
    -0.08
    笥
    -0.08
    韫
    -0.08
    ΅
    -0.07
    Ӕ
    -0.07
    🇱
    -0.07
    põ
    -0.07
    废气
    -0.07
     podium
    -0.07
    POSITIVE LOGITS
     lak
    0.08
    חלת
    0.07
     drafts
    0.07
     lov
    0.07
    -clock
    0.07
    _PROC
    0.07
    dots
    0.07
     contractors
    0.07
    (tool
    0.07
    jac
    0.07
    Act Density 0.021%

    No Known Activations