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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saw
    -0.07
     Э
    -0.07
    Name
    -0.06
    onymous
    -0.06
     saw
    -0.06
     vodka
    -0.06
    VOID
    -0.06
    .`|`↵
    -0.06
     inmates
    -0.06
     roofing
    -0.06
    POSITIVE LOGITS
     треб
    0.07
     Fay
    0.06
    Laugh
    0.06
    _TB
    0.06
    |i
    0.06
    UIApplicationDelegate
    0.06
    igung
    0.06
    λευτα
    0.06
     تیر
    0.06
    ']*
    0.06
    Act Density 0.006%

    No Known Activations