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

    Neuronpedia

    INDEX
    Explanations

    percentages, parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flutter
    -0.06
    (PATH
    -0.06
    dup
    -0.06
    	ctrl
    -0.06
     sarcast
    -0.06
     chin
    -0.06
    ortal
    -0.06
     shaded
    -0.06
    thag
    -0.06
     thrift
    -0.06
    POSITIVE LOGITS
    涉
    0.06
    .apiUrl
    0.06
    updatedAt
    0.06
    Owned
    0.06
    ‐‐
    0.06
    $j
    0.06
    _quad
    0.06
     kus
    0.06
     encourages
    0.06
     ){↵
    0.06
    Act Density 0.023%

    No Known Activations