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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poorer
    -0.08
     Equivalent
    -0.08
    .Normal
    -0.07
    ulators
    -0.07
     Etats
    -0.07
    .Act
    -0.07
     Warwick
    -0.07
     Mink
    -0.07
    生活
    -0.07
    .Point
    -0.07
    POSITIVE LOGITS
    _PREFIX
    0.14
    _prefix
    0.14
     prefix
    0.14
    Prefix
    0.14
    -prefix
    0.14
     prefixes
    0.14
    PREFIX
    0.13
    .prefix
    0.13
    prefix
    0.13
     PREFIX
    0.13
    Act Density 0.010%

    No Known Activations