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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     webhook
    0.56
     presets
    0.56
     iCloud
    0.55
     👇
    0.53
    についても
    0.52
    falfa
    0.50
     servidores
    0.49
     responsibly
    0.49
    োসিয়ে
    0.49
     Dropbox
    0.49
    POSITIVE LOGITS
    rm
    0.94
    bf
    0.88
    sf
    0.76
     rm
    0.71
    normal
    0.67
     bf
    0.64
     normal
    0.62
    tt
    0.60
     sf
    0.60
    正常的
    0.60
    Act Density 0.022%

    No Known Activations