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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쌓
    -0.07
    Let
    -0.07
     texte
    -0.07
    使い
    -0.07
     capacit
    -0.07
     Tennis
    -0.06
    .tp
    -0.06
     mogelijk
    -0.06
    �
    -0.06
     zobowiąz
    -0.06
    POSITIVE LOGITS
     monitors
    0.07
    顺序
    0.07
    ;"
    0.07
    .kernel
    0.07
    abajo
    0.07
    pb
    0.07
    sources
    0.07
    bay
    0.07
     />\
    0.07
     ,'
    0.06
    Act Density 0.001%

    No Known Activations