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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pem
    -0.07
    @RestController
    -0.07
    Constraint
    -0.06
    玱
    -0.06
     lawyer
    -0.06
    tensor
    -0.06
     Photographer
    -0.06
     allegedly
    -0.06
     MOV
    -0.06
     minor
    -0.06
    POSITIVE LOGITS
    눌
    0.08
    ょう
    0.07
     watches
    0.07
    的发生
    0.06
    _filters
    0.06
     emptied
    0.06
     ogląda
    0.06
    あなたの
    0.06
     tabela
    0.06
    تنظيم
    0.06
    Act Density 0.001%

    No Known Activations