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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gerry
    -0.07
    Sil
    -0.07
    theast
    -0.06
    ++]=
    -0.06
    olders
    -0.06
     blacklist
    -0.06
    |=
    -0.06
     Aberdeen
    -0.06
    сят
    -0.06
    	http
    -0.06
    POSITIVE LOGITS
     FAILURE
    0.07
     Animation
    0.06
     awakened
    0.06
    uppe
    0.06
    _can
    0.06
     THERE
    0.06
    خص
    0.06
     ساز
    0.06
    respuesta
    0.06
     INTERNAL
    0.06
    Act Density 0.000%

    No Known Activations