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

    Neuronpedia

    INDEX
    Explanations

    hard work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.68
    c
    0.67
    cale
    0.65
    et
    0.64
    cape
    0.63
    am
    0.60
    ine
    0.60
    ich
    0.59
    تها
    0.59
    ent
    0.59
    POSITIVE LOGITS
    는
    0.81
    AL
    0.79
    EY
    0.62
    λλ
    0.62
    IRED
    0.62
     Học
    0.61
     sawdust
    0.60
     đức
    0.60
    spiderX
    0.60
     একাডেমিক
    0.60
    Act Density 0.004%

    No Known Activations