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

    Neuronpedia

    INDEX
    Explanations

    say AD

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Sprite
    -0.07
    -foot
    -0.07
    :\\
    -0.07
    Sp
    -0.06
    _DETECT
    -0.06
    :",
    -0.06
     flashy
    -0.06
     ESPN
    -0.06
     prisons
    -0.06
     нього
    -0.06
    POSITIVE LOGITS
    _DIM
    0.07
    AsyncResult
    0.07
    AutoresizingMask
    0.07
    HasBeenSet
    0.06
    _pas
    0.06
    δρα
    0.06
    CppGeneric
    0.06
    mathrm
    0.06
     proficiency
    0.06
     Fransız
    0.06
    Act Density 0.001%

    No Known Activations