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

    Neuronpedia

    INDEX
    Explanations

    string manipulation and encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    핼
    0.41
     teachers
    0.38
     בצ
    0.38
    emit
    0.37
    ilai
    0.37
    aline
    0.37
     convened
    0.36
     convene
    0.36
    seudo
    0.36
     Script
    0.36
    POSITIVE LOGITS
     trim
    0.55
    trim
    0.52
    substr
    0.48
     substr
    0.47
    宻
    0.46
    ;%(
    0.45
     utf
    0.43
    Trim
    0.43
     mb
    0.42
     str
    0.42
    Act Density 0.005%

    No Known Activations