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

    Neuronpedia

    INDEX
    Explanations

    shell commands and scripting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.83
    t
    0.77
    de
    0.77
    то
    0.68
    dx
    0.65
    ت
    0.65
     в
    0.64
    اً
    0.61
    ш
    0.60
    _
    0.59
    POSITIVE LOGITS
     bash
    0.83
     Bash
    0.73
    Bash
    0.68
    bash
    0.67
     booty
    0.64
     oblique
    0.61
     uncontrollable
    0.61
    ’
    0.60
     honorable
    0.59
     exhaustion
    0.59
    Act Density 0.019%

    No Known Activations