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

    Neuronpedia

    INDEX
    Explanations

    danger, survival, or answer prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     material
    0.82
     renormalization
    0.78
     assuntos
    0.76
     appropriation
    0.75
     Material
    0.75
     functions
    0.74
     element
    0.71
     mineral
    0.70
     Mineral
    0.70
    mun
    0.69
    POSITIVE LOGITS
    Ako
    0.91
    Hvis
    0.89
    Yeni
    0.78
    GAME
    0.77
    ֥
    0.77
    ക്കുന്ന
    0.77
    Marne
    0.76
    etext
    0.76
    Picked
    0.76
    Seperti
    0.76
    Act Density 0.004%

    No Known Activations