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

    Neuronpedia

    INDEX
    Explanations

    illegal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Volvo
    -0.08
    COME
    -0.07
     Fiji
    -0.07
    盈
    -0.07
    痛点
    -0.06
     boon
    -0.06
     ITEM
    -0.06
    暮
    -0.06
    黄昏
    -0.06
    CEO
    -0.06
    POSITIVE LOGITS
    )',
    0.08
     syntax
    0.07
    lararası
    0.07
     rootReducer
    0.07
    女足
    0.07
     ===>
    0.07
    од
    0.07
    되어
    0.07
    trace
    0.07
     palabra
    0.07
    Act Density 0.012%

    No Known Activations