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

    Neuronpedia

    INDEX
    Explanations

    ordinary, everyday, normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estratég
    0.75
    ține
    0.68
    vorschau
    0.65
     glPushMatrix
    0.65
     महंगा
    0.65
     estratégica
    0.64
    óry
    0.63
     estratégico
    0.63
    irittura
    0.62
    enschutz
    0.62
    POSITIVE LOGITS
     everyday
    3.74
     ordinary
    3.49
     mundane
    3.06
     Everyday
    2.94
     normal
    2.92
    ordinary
    2.92
    日常
    2.85
     Ordinary
    2.80
     повседнев
    2.80
    Ordinary
    2.74
    Act Density 2.788%

    No Known Activations