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

    Neuronpedia

    INDEX
    Explanations

    expressions of visual appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    look like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.73
    OGND
    -0.69
     ivelany
    -0.59
     Audiodateien
    -0.59
    LookAnd
    -0.58
    abestanden
    -0.56
    Kariera
    -0.55
    endphp
    -0.55
    endregion
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    POSITIVE LOGITS
    มาะ
    0.45
     vern
    0.42
     Fils
    0.40
    SceneManagement
    0.40
     essentials
    0.40
     complementary
    0.39
     blin
    0.38
     stage
    0.38
     ots
    0.38
     Stair
    0.37
    Act Density 0.014%

    No Known Activations