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

    Neuronpedia

    INDEX
    Explanations

    code context or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ждён
    0.55
    मैन
    0.52
    Су
    0.52
    characterized
    0.52
    noisy
    0.52
    கிர
    0.52
    recognized
    0.51
    менов
    0.51
    פת
    0.50
    𝒹
    0.50
    POSITIVE LOGITS
     role
    0.46
     lattice
    0.45
    وار
    0.44
    ൂര
    0.44
     workpiece
    0.43
     voyage
    0.42
     lima
    0.42
     sparrow
    0.42
     cli
    0.42
    螂
    0.42
    Act Density 0.000%

    No Known Activations