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

    Neuronpedia

    INDEX
    Explanations

    identifying specific things and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $+
    0.42
    Prime
    0.40
     CE
    0.40
     marts
    0.40
     apel
    0.39
    Sonic
    0.39
     throng
    0.39
    INGS
    0.38
    ÉR
    0.38
     inch
    0.38
    POSITIVE LOGITS
    timestep
    0.40
    दायक
    0.39
    呕
    0.39
    }());
    0.38
    ptitle
    0.38
    과학
    0.38
    궤
    0.38
     Etat
    0.38
    ismarck
    0.37
     visualisation
    0.37
    Act Density 0.000%

    No Known Activations