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

    Neuronpedia

    INDEX
    Explanations

    binding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bere
    -0.07
    .registry
    -0.07
    adaptiveStyles
    -0.06
    /report
    -0.06
    㶳
    -0.06
     candies
    -0.06
    谏
    -0.06
     PE
    -0.06
    沦
    -0.06
     XO
    -0.06
    POSITIVE LOGITS
     THC
    0.07
     renders
    0.07
    我现在
    0.07
    läuft
    0.07
    scriptions
    0.07
     entfer
    0.07
    ertos
    0.07
    amaged
    0.06
     triggered
    0.06
     mounting
    0.06
    Act Density 0.006%

    No Known Activations