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

    Neuronpedia

    INDEX
    Explanations

    conditional logic `if` statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     με
    0.47
     Τ
    0.46
     গলা
    0.39
     Ι
    0.38
     Α
    0.37
    τε
    0.36
     ο
    0.35
     Μ
    0.35
     ι
    0.34
    Τ
    0.34
    POSITIVE LOGITS
    assumption
    0.45
     എന്നാൽ
    0.42
     അല്ലെങ്കിൽ
    0.41
    ี
    0.39
    存档备份
    0.39
    istic
    0.38
    पाकिस्तान
    0.38
    but
    0.38
     لكن
    0.38
     perspect
    0.37
    Act Density 0.070%

    No Known Activations