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

    Neuronpedia

    INDEX
    Explanations

    advice and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    英語
    -0.07
    :@""
    -0.06
     카
    -0.06
    らしい
    -0.06
    (resolve
    -0.06
    пос
    -0.06
    _equ
    -0.06
    _IDENT
    -0.06
     SUP
    -0.06
    новаж
    -0.06
    POSITIVE LOGITS
     Pic
    0.08
     hue
    0.06
     Depths
    0.06
     ing
    0.06
    angered
    0.06
     overlooked
    0.06
     suck
    0.06
     helpful
    0.06
     each
    0.06
     ValueType
    0.06
    Act Density 0.011%

    No Known Activations