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

    Neuronpedia

    INDEX
    Explanations

    HTML button closing tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *,
    0.44
     वगैरह
    0.38
    ［
    0.38
    °,
    0.37
    juana
    0.37
    흄
    0.36
     COMPANIES
    0.36
    ↵↵↵↵↵
    0.35
     noxious
    0.34
     mavenCentral
    0.34
    POSITIVE LOGITS
    ">{{
    0.63
    ">(
    0.63
    ">$
    0.59
    ">
    0.58
    ">${
    0.58
    ">'
    0.58
    ">%
    0.57
    ">[
    0.57
    "><?
    0.56
    ">{
    0.56
    Act Density 0.015%

    No Known Activations