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

    Neuronpedia

    INDEX
    Explanations

    light warms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IMHO
    0.52
     fucked
    0.49
     pissed
    0.47
     !!!!
    0.46
     WTF
    0.46
     IMO
    0.45
     sebag
    0.44
     +/-
    0.44
     shitty
    0.43
     assh
    0.43
    POSITIVE LOGITS
     soltanto
    0.77
     굉장
    0.72
     aisément
    0.70
     swiftly
    0.69
     نخست
    0.69
     எனும்
    0.68
     marvelous
    0.67
    应当
    0.67
     ialah
    0.67
     ஓர்
    0.66
    Act Density 0.337%

    No Known Activations