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

    Neuronpedia

    INDEX
    Explanations

    cardinal directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diluted
    -0.07
    .dimensions
    -0.07
    _supplier
    -0.07
     Preserve
    -0.07
     insects
    -0.07
    _recall
    -0.07
    (insert
    -0.07
    dere
    -0.07
    ประชาชน
    -0.07
     observational
    -0.07
    POSITIVE LOGITS
    �
    0.07
    ają
    0.07
     若要
    0.07
    ,['
    0.07
    [group
    0.07
    阃
    0.07
    🐓
    0.07
    importe
    0.06
    otts
    0.06
    RGBO
    0.06
    Act Density 0.002%

    No Known Activations