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

    Neuronpedia

    INDEX
    Explanations

    definition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snippets
    -0.07
     bird
    -0.06
    -method
    -0.06
    _identity
    -0.06
     sei
    -0.06
    쳐
    -0.06
     Checks
    -0.06
     Tour
    -0.06
     party
    -0.06
     lut
    -0.06
    POSITIVE LOGITS
    ..↵
    0.06
    Stopping
    0.06
    Christmas
    0.06
    >O
    0.06
    ентами
    0.06
    .JsonProperty
    0.06
     runaway
    0.06
     DataTypes
    0.06
     Marx
    0.06
    esterday
    0.06
    Act Density 0.018%

    No Known Activations