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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    These
    -0.07
     MainAxisAlignment
    -0.06
     Sly
    -0.06
     �
    -0.06
     Ingram
    -0.06
     Joyce
    -0.06
    -0.06
    <WebElement
    -0.06
    (ax
    -0.06
    》↵
    -0.06
    POSITIVE LOGITS
    kö
    0.09
    kaz
    0.08
    anna
    0.07
    worth
    0.07
    annon
    0.07
    RC
    0.07
    ria
    0.07
    itzer
    0.07
    ané
    0.07
    ari
    0.07
    Act Density 1.201%

    No Known Activations