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

    Neuronpedia

    INDEX
    Explanations

    game hacking and cheating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portugal
    0.59
    Portug
    0.55
    Japan
    0.53
     Portug
    0.52
    onica
    0.51
    Italian
    0.51
    isjon
    0.48
    igrant
    0.48
    itas
    0.48
    igator
    0.48
    POSITIVE LOGITS
    袒
    0.50
    েম
    0.49
     CS
    0.49
     CSM
    0.47
     lửa
    0.47
     vyb
    0.47
     সশস্ত্র
    0.46
    cS
    0.46
    ക്കി
    0.46
    افي
    0.46
    Act Density 0.005%

    No Known Activations