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

    Neuronpedia

    INDEX
    Explanations

    divide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adults
    -0.08
     geschlossen
    -0.08
     receptionist
    -0.08
    植
    -0.08
    成人
    -0.07
     plantar
    -0.07
     JAN
    -0.07
     newer
    -0.07
     adult
    -0.07
     swear
    -0.07
    POSITIVE LOGITS
     denominator
    0.10
     denomin
    0.09
    excluded
    0.08
     precar
    0.08
    onneur
    0.08
     precautions
    0.08
     delicate
    0.08
     avoided
    0.08
    iable
    0.08
    icen
    0.08
    Act Density 0.022%

    No Known Activations