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

    Neuronpedia

    INDEX
    Explanations

    Resonance Strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unsuitable
    0.44
     মিলন
    0.40
    燕
    0.40
     slice
    0.39
    Slice
    0.39
     meal
    0.38
     Slice
    0.38
     Cocktail
    0.38
     diarios
    0.37
    鍘
    0.37
    POSITIVE LOGITS
    Ult
    0.40
     entreprise
    0.40
     Ult
    0.39
     الشركات
    0.38
     typ
    0.37
    রেক
    0.36
    黄金
    0.36
    Strength
    0.35
     بروز
    0.35
    㽛
    0.35
    Act Density 0.000%

    No Known Activations