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

    Neuronpedia

    INDEX
    Explanations

    code keywords and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     કે
    0.43
     originale
    0.40
     Ім
    0.37
     tuleb
    0.35
     original
    0.34
     го
    0.34
     manquer
    0.33
     മുതൽ
    0.33
     รวมถึง
    0.33
    ।
    0.33
    POSITIVE LOGITS
    false
    0.44
    lys
    0.40
    weis
    0.40
    conditional
    0.38
    i
    0.37
    alas
    0.37
    another
    0.37
    omic
    0.36
    øj
    0.36
    いま
    0.36
    Act Density 0.018%

    No Known Activations