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

    Neuronpedia

    INDEX
    Explanations

    crystal clear, remain silent, between men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interfering
    0.50
     malattie
    0.50
    𝗁
    0.50
     sickly
    0.50
     kó
    0.49
     nascita
    0.49
     malattia
    0.48
     пен
    0.48
     miglia
    0.48
     jungen
    0.47
    POSITIVE LOGITS
     B
    0.58
    idar
    0.57
    5
    0.56
    aria
    0.55
    on
    0.54
    ST
    0.53
    ars
    0.53
    B
    0.52
     L
    0.52
    ase
    0.52
    Act Density 0.000%

    No Known Activations