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

    Neuronpedia

    INDEX
    Explanations

    suffix -ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bimestre
    0.53
     nici
    0.52
     மகிழ்ச்ச
    0.52
     worship
    0.49
    に向けて
    0.49
     concreta
    0.49
     indiquant
    0.49
    ެވެ
    0.48
     racc
    0.48
    ﭥ
    0.47
    POSITIVE LOGITS
    л
    0.51
    er
    0.45
    Observable
    0.45
    iced
    0.42
    Texas
    0.41
    ectic
    0.41
    eline
    0.41
    ano
    0.40
    attham
    0.40
    压
    0.39
    Act Density 0.001%

    No Known Activations