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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ellipse
    -0.07
    athlon
    -0.07
     gridBagConstraints
    -0.07
     Café
    -0.06
    /aws
    -0.06
     shaded
    -0.06
     liability
    -0.06
    shade
    -0.06
    ponible
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     RET
    0.06
    iatrics
    0.06
       ↵↵
    0.06
    Charles
    0.06
    >Action
    0.06
    iatric
    0.06
    ลา
    0.06
    岛
    0.05
    яв
    0.05
    EObject
    0.05
    Act Density 0.076%

    No Known Activations