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

    Neuronpedia

    INDEX
    Explanations

    save

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     düğ
    -0.06
    オン
    -0.06
     misog
    -0.06
    onn
    -0.06
    olley
    -0.06
     Norfolk
    -0.06
    érc
    -0.06
     limited
    -0.06
    řik
    -0.06
     代
    -0.06
    POSITIVE LOGITS
    abis
    0.07
    gis
    0.06
    危
    0.06
     extravag
    0.06
     hobbies
    0.06
    病
    0.06
    toggle
    0.06
     Weed
    0.06
     проект
    0.06
    ={{
    0.06
    Act Density 0.000%

    No Known Activations