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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winger
    -0.07
     enctype
    -0.06
    olate
    -0.06
    _FIELDS
    -0.06
    τεί
    -0.06
    campo
    -0.06
     زیرا
    -0.06
    else
    -0.06
     Philippines
    -0.06
     giden
    -0.06
    POSITIVE LOGITS
     memoir
    0.07
     observe
    0.07
     negatives
    0.07
    orts
    0.06
     민
    0.06
     Disorders
    0.06
    独
    0.06
     roasted
    0.06
    reported
    0.06
     اك
    0.06
    Act Density 0.005%

    No Known Activations