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

    Neuronpedia

    INDEX
    Explanations

    measurement units

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coder
    -0.06
     specifications
    -0.06
    _RGBA
    -0.06
     Inspection
    -0.06
    _SCORE
    -0.06
    Printf
    -0.06
    ी
    -0.06
     info
    -0.06
     CreateUser
    -0.06
    Link
    -0.06
    POSITIVE LOGITS
    ";}↵
    0.07
     dominated
    0.07
    ilded
    0.07
     strs
    0.06
    von
    0.06
     \"{
    0.06
    '>↵↵
    0.06
     ";
↵
    0.06
    ilih
    0.06
    _tE
    0.06
    Act Density 0.004%

    No Known Activations