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

    Neuronpedia

    INDEX
    Explanations

    manner adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supuesto
    0.74
    려는
    0.73
     terletak
    0.69
     volto
    0.69
    ানার
    0.65
     suficiente
    0.65
     evidente
    0.65
    เผย
    0.64
     lắm
    0.64
     যতক্ষণ
    0.64
    POSITIVE LOGITS
     secara
    1.81
     informally
    1.71
     Secara
    1.64
     academically
    1.63
     creatively
    1.63
     electronically
    1.60
     economically
    1.59
     electrically
    1.57
     analytically
    1.57
     professionally
    1.55
    Act Density 0.349%

    No Known Activations