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

    Neuronpedia

    INDEX
    Explanations

    ts-node or typescript files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்
    0.42
    onSubmit
    0.40
    vents
    0.38
    ществ
    0.38
     সমর্থ
    0.38
     useContext
    0.38
     stets
    0.38
    დომ
    0.38
    偪
    0.37
     Cord
    0.36
    POSITIVE LOGITS
    指令
    0.51
    expect
    0.44
    Expect
    0.43
     expectativa
    0.41
     expectancy
    0.40
    nog
    0.40
     inexperienced
    0.40
    ino
    0.39
    JH
    0.39
    unsafe
    0.38
    Act Density 0.000%

    No Known Activations