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

    Neuronpedia

    INDEX
    Explanations

    step-by-step explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    надца
    0.45
    liği
    0.44
    codon
    0.43
    imagen
    0.43
    δρο
    0.42
    ꗥ
    0.42
    preliquidacion
    0.42
    წინ
    0.42
    доро
    0.42
    лам
    0.41
    POSITIVE LOGITS
     by
    0.60
    wise
    0.47
     schemes
    0.45
     By
    0.44
     slowly
    0.44
    by
    0.44
     वाइज
    0.43
     scheme
    0.42
     study
    0.41
    By
    0.41
    Act Density 0.012%

    No Known Activations