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

    Neuronpedia

    INDEX
    Explanations

    S/ subsequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    1.21
    etting
    1.02
    to
    0.99
    em
    0.93
    et
    0.88
    p
    0.87
    ter
    0.84
    ub
    0.82
    teki
    0.80
    eq
    0.80
    POSITIVE LOGITS
    ildenafil
    1.01
    essional
    0.97
    ylvan
    0.91
    ஸின்
    0.90
    atori
    0.85
    velte
    0.85
    pero
    0.83
     cerevisiae
    0.80
    essment
    0.78
    ஸுக்கு
    0.78
    Act Density 0.284%

    No Known Activations