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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apanese
    -0.07
     長
    -0.06
    ’ve
    -0.06
    dzi
    -0.06
    izoph
    -0.06
    оят
    -0.06
     Nex
    -0.06
     Teacher
    -0.06
    �
    -0.06
    isay
    -0.06
    POSITIVE LOGITS
     Affero
    0.07
     adına
    0.07
     전에
    0.06
     •
    0.06
     worth
    0.06
     sélection
    0.06
     své
    0.06
    selected
    0.06
    งเป
    0.06
    该
    0.06
    Act Density 0.001%

    No Known Activations