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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WebService
    -0.08
    🎥
    -0.07
    שירות
    -0.07
    ◓
    -0.07
    ruptcy
    -0.07
    Drug
    -0.07
     Prostit
    -0.07
    美味し
    -0.07
     In
    -0.07
    (Sprite
    -0.06
    POSITIVE LOGITS
     None
    0.07
    >$
    0.07
    0.07
    buff
    0.07
    .Box
    0.07
    _ITER
    0.07
    0.07
    <div
    0.07
    кер
    0.07
    DF
    0.06
    Act Density 0.020%

    No Known Activations