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

    Neuronpedia

    INDEX
    Explanations

    remember when you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arctica
    1.15
    yeong
    1.13
     deporte
    1.13
     riječi
    1.12
    iş
    1.11
    yectos
    1.10
     rispond
    1.09
    acoli
    1.09
    calibur
    1.06
    providing
    1.05
    POSITIVE LOGITS
    なんと
    1.06
     inversion
    1.05
     Darling
    0.97
     sacred
    0.96
     Warriors
    0.95
    GameOver
    0.94
     cows
    0.93
    女孩
    0.92
    റും
    0.92
    违
    0.91
    Act Density 0.001%

    No Known Activations