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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جامع
    -0.07
    辅
    -0.07
    iblings
    -0.06
     chooses
    -0.06
     stepping
    -0.06
    產品
    -0.06
     API
    -0.06
     earned
    -0.06
     board
    -0.06
    -world
    -0.06
    POSITIVE LOGITS
    -Token
    0.06
    (ln
    0.06
    主人
    0.06
    ="<<
    0.06
    ################################################################################
    0.06
     epsilon
    0.06
    €€€€€€€€
    0.06
    .trip
    0.06
    enght
    0.06
     тих
    0.06
    Act Density 0.026%

    No Known Activations