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

    Neuronpedia

    INDEX
    Explanations

    HS code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ions
    0.74
    apes
    0.71
    ightly
    0.70
    ători
    0.67
    ilien
    0.67
    onar
    0.66
     Every
    0.64
    ailed
    0.64
    iers
    0.64
    ails
    0.64
    POSITIVE LOGITS
    L
    0.69
    Map
    0.68
    Recipe
    0.66
     L
    0.63
    Sentence
    0.63
     nailing
    0.62
     ল
    0.62
    গ্রন্থ
    0.61
    Log
    0.61
     ಲ
    0.60
    Act Density 0.000%

    No Known Activations