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

    Neuronpedia

    INDEX
    Explanations

    URL and markdown formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vultures
    0.42
     is
    0.39
    志森
    0.39
     ~
    0.38
     Fairview
    0.35
     hallways
    0.35
     headphones
    0.35
     Monkeys
    0.34
     С
    0.34
     magicians
    0.34
    POSITIVE LOGITS
    R
    0.56
    ل
    0.54
    ку
    0.48
    و
    0.47
    D
    0.47
    f
    0.46
    نا
    0.45
    ون
    0.44
    ным
    0.43
    ور
    0.43
    Act Density 6.282%

    No Known Activations