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

    Neuronpedia

    INDEX
    Explanations

    arguments and evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chessboard
    0.45
     invece
    0.42
     schrift
    0.41
     decompose
    0.41
     corpses
    0.41
     compleja
    0.41
     complex
    0.41
     positron
    0.41
     usu
    0.41
     koriste
    0.40
    POSITIVE LOGITS
     Injuries
    0.58
    argu
    0.57
    despite
    0.50
     overcame
    0.49
     suffered
    0.49
    consistency
    0.49
     Argu
    0.49
    Unfortunately
    0.49
    has
    0.48
     arguably
    0.47
    Act Density 0.003%

    No Known Activations