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

    Neuronpedia

    INDEX
    Explanations

    В

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oxel
    -0.07
    Prototype
    -0.07
     todas
    -0.07
     collaps
    -0.06
    ují
    -0.06
    _MS
    -0.06
     latitude
    -0.06
     recounted
    -0.06
     verwendet
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    wig
    0.07
     responder
    0.07
    복지
    0.07
    /")
    0.07
     हर
    0.06
    (show
    0.06
    """
↵
↵
    0.06
    ailing
    0.06
    .ORDER
    0.06
    ,↵↵
    0.06
    Act Density 0.014%

    No Known Activations