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

    Neuronpedia

    INDEX
    Explanations

    Upwork and freelance work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fuck
    0.62
    Fuck
    0.59
    僕は
    0.52
    🤙
    0.51
     僕
    0.47
    伱
    0.47
     ✅
    0.47
    🖕
    0.47
     fucked
    0.46
    僕
    0.46
    POSITIVE LOGITS
     hubby
    0.77
     lovely
    0.68
     awful
    0.61
     *
    0.60
     yummy
    0.59
    lovely
    0.59
     horrid
    0.59
     really
    0.58
     terribly
    0.58
     tiny
    0.57
    Act Density 0.004%

    No Known Activations