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

    Neuronpedia

    INDEX
    Explanations

    formatting instructions, lists, accents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PES
    0.50
    ocere
    0.47
    סים
    0.44
     수가
    0.43
     mavenCentral
    0.42
    牀
    0.42
     satisfactor
    0.42
    =-
    0.42
    APAN
    0.42
     motiva
    0.42
    POSITIVE LOGITS
    G
    0.43
    u
    0.42
    C
    0.41
    rugated
    0.40
     antérieur
    0.39
    އ
    0.39
    appreci
    0.39
     অঞ্চলের
    0.39
    water
    0.38
     elevation
    0.37
    Act Density 0.008%

    No Known Activations