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

    Neuronpedia

    INDEX
    Explanations

    866 crisis support numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     covariant
    0.36
     BlueprintName
    0.35
     DataFrame
    0.35
    ScriptObject
    0.34
     nonparametric
    0.33
    bindingFields
    0.33
     Hamiltonian
    0.33
    gaxModule
    0.32
     Riemannian
    0.32
    オブジェクト
    0.32
    POSITIVE LOGITS
    re
    0.42
    Help
    0.38
    ’
    0.38
     the
    0.38
    Com
    0.38
    I
    0.37
    ↵↵
    0.36
    M
    0.34
    the
    0.34
     Help
    0.34
    Act Density 0.055%

    No Known Activations