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

    Neuronpedia

    INDEX
    Explanations

    types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    〇
    -0.06
    	sock
    -0.06
     severity
    -0.06
     probation
    -0.06
    ichel
    -0.06
     مص
    -0.06
    HOST
    -0.06
    Players
    -0.06
     imm
    -0.06
     張
    -0.06
    POSITIVE LOGITS
    918
    0.09
    olk
    0.07
     Tyson
    0.06
    (labels
    0.06
    /gui
    0.06
    rompt
    0.06
    poke
    0.06
    liable
    0.06
    сім
    0.06
     {}",
    0.06
    Act Density 0.000%

    No Known Activations