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

    Neuronpedia

    INDEX
    Explanations

    state updates with useState

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tikai
    0.43
    ynie
    0.42
     zerstört
    0.40
     pédagog
    0.40
     निशाने
    0.40
     Mili
    0.39
     ምንም
    0.38
     fdPar
    0.38
     tomonidan
    0.38
     pathological
    0.38
    POSITIVE LOGITS
    Definition
    0.43
     /
    0.40
    S
    0.39
    (
    0.38
    ማ
    0.38
     lighten
    0.36
    t
    0.36
    days
    0.36
    v
    0.36
    Stepper
    0.35
    Act Density 0.001%

    No Known Activations