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

    Neuronpedia

    INDEX
    Explanations

    Universities or academics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    321
    -0.06
     Sokol
    -0.06
    �
    -0.06
     drink
    -0.06
    imum
    -0.06
     weld
    -0.06
     hang
    -0.06
    ih
    -0.06
    .Empty
    -0.06
     уси
    -0.06
    POSITIVE LOGITS
     roleName
    0.07
     mans
    0.06
    =label
    0.06
    čast
    0.06
    JE
    0.06
    (post
    0.06
     UserDefaults
    0.06
     argc
    0.06
     PA
    0.06
    ,buf
    0.06
    Act Density 0.009%

    No Known Activations