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

    Neuronpedia

    INDEX
    Explanations

    selling offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mark
    0.46
    ни
    0.45
     Computer
    0.45
     That
    0.44
     Tracy
    0.44
     Institutional
    0.44
    Mark
    0.43
     "...
    0.43
     Grant
    0.43
     Blank
    0.43
    POSITIVE LOGITS
     forecasts
    0.54
     листья
    0.52
    𝒞
    0.52
    efeuille
    0.51
    cado
    0.49
    azah
    0.49
     wrongfully
    0.49
     warmly
    0.48
    esus
    0.48
     assaulted
    0.48
    Act Density 0.002%

    No Known Activations