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

    Neuronpedia

    INDEX
    Explanations

    ask, without, fucking, complexity, transformation, deadly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    0.50
    ang
    0.49
    est
    0.49
    l
    0.49
    ors
    0.47
    es
    0.46
    ation
    0.45
    ago
    0.44
    ch
    0.43
    ble
    0.42
    POSITIVE LOGITS
    है
    0.56
    ാരി
    0.54
    LEMN
    0.52
    พาะ
    0.50
     chiff
    0.50
    ᓃ
    0.49
     relâche
    0.48
     cinereo
    0.48
    𝔯
    0.48
    '}$
    0.48
    Act Density 0.001%

    No Known Activations