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

    Neuronpedia

    INDEX
    Explanations

    launching or starting something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    緯
    0.40
     Eventually
    0.40
     तुम्हारे
    0.39
     worsen
    0.39
     двор
    0.38
     contemplate
    0.38
     mógł
    0.38
     Worse
    0.38
    Penalty
    0.37
     Ever
    0.37
    POSITIVE LOGITS
    Launching
    0.49
    launch
    0.47
     launch
    0.46
     launching
    0.43
     Launch
    0.43
    LAUNCH
    0.41
    Launch
    0.40
     memulai
    0.39
    외
    0.38
    inité
    0.38
    Act Density 0.000%

    No Known Activations