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

    Neuronpedia

    INDEX
    Explanations

    code importing modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exposure
    0.72
     Moderne
    0.68
     Maler
    0.68
     vecino
    0.67
     Lik
    0.67
     Erg
    0.66
     outbound
    0.66
     adrenergic
    0.66
     skyrock
    0.65
    ದ್ದು
    0.64
    POSITIVE LOGITS
    import
    3.99
     import
    3.67
    Import
    2.95
     Import
    2.80
     importing
    2.70
     imports
    2.65
     importation
    2.48
     imported
    2.48
     importar
    2.40
     Importing
    2.28
    Act Density 0.283%

    No Known Activations