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

    Neuronpedia

    INDEX
    Explanations

    Assumptions and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ediyor
    -0.07
    WORD
    -0.06
     tasar
    -0.06
    ��取
    -0.06
    Integer
    -0.06
    .et
    -0.06
    رض
    -0.06
     Cars
    -0.06
     charset
    -0.06
     '|
    -0.05
    POSITIVE LOGITS
    Specific
    0.07
    Winter
    0.07
     Pod
    0.07
     krát
    0.07
     placed
    0.07
    .vue
    0.07
     qualify
    0.06
    Andre
    0.06
    -beta
    0.06
     Cave
    0.06
    Act Density 0.052%

    No Known Activations