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

    Neuronpedia

    INDEX
    Explanations

    timer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Temperature
    -0.07
    Faces
    -0.07
    Finite
    -0.07
     price
    -0.07
    Limits
    -0.06
    PLIER
    -0.06
    ango
    -0.06
     Prov
    -0.06
    3
    -0.06
     skepticism
    -0.06
    POSITIVE LOGITS
     cham
    0.07
    -aff
    0.07
    (forKey
    0.06
     прож
    0.06
     indo
    0.06
    erty
    0.06
     harass
    0.06
     pořad
    0.06
    ndern
    0.06
     ประ
    0.06
    Act Density 0.014%

    No Known Activations