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

    Neuronpedia

    INDEX
    Explanations

    text adventure game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    0.53
    Firm
    0.50
    $)
    0.48
    losti
    0.47
     Тя
    0.46
    ленным
    0.45
    Dense
    0.44
     Namun
    0.43
    ября
    0.43
    Bias
    0.43
    POSITIVE LOGITS
    مل
    0.62
     ranged
    0.59
     bookings
    0.54
    می
    0.53
    سر
    0.53
     right
    0.52
    ng
    0.50
    ms
    0.49
    ма
    0.49
     mafia
    0.49
    Act Density 0.000%

    No Known Activations