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

    Neuronpedia

    INDEX
    Explanations

    configuration files/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilang
    -0.07
    ato
    -0.07
     browned
    -0.07
    aka
    -0.07
    👏
    -0.07
     symptomatic
    -0.07
     booming
    -0.07
    neck
    -0.07
    bereitung
    -0.07
    unding
    -0.07
    POSITIVE LOGITS
     cie
    0.09
    $file
    0.08
     descendant
    0.08
     không
    0.08
     fragment
    0.08
    lucht
    0.08
    чы
    0.07
     laser
    0.07
     môi
    0.07
     mật
    0.07
    Act Density 0.000%

    No Known Activations