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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     `${
    -0.07
     Running
    -0.06
     clan
    -0.06
    사는
    -0.06
    stav
    -0.06
     blow
    -0.06
     interactive
    -0.06
     شن
    -0.06
     Border
    -0.06
     Perc
    -0.06
    POSITIVE LOGITS
     normalize
    0.07
    *cos
    0.07
    	ast
    0.06
    _SOC
    0.06
    getAs
    0.06
    *out
    0.06
    metis
    0.06
    하다
    0.06
    华
    0.06
    _ms
    0.06
    Act Density 0.007%

    No Known Activations