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

    Neuronpedia

    INDEX
    Explanations

    code functions/subroutines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sword
    -0.07
    xFE
    -0.07
    уйте
    -0.07
     nguyên
    -0.06
    jquery
    -0.06
     bothering
    -0.06
     zajist
    -0.06
     چشم
    -0.06
    以前
    -0.06
     pertaining
    -0.06
    POSITIVE LOGITS
    MODEL
    0.07
    	unset
    0.06
    _OPTIONS
    0.06
     ؛
    0.06
    tri
    0.06
    setMax
    0.06
    Ga
    0.06
    Amb
    0.06
     abduction
    0.06
    Warning
    0.06
    Act Density 0.005%

    No Known Activations