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

    Neuronpedia

    INDEX
    Explanations

    references to underground environments or contexts

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

    underground

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ciutto
    -0.57
     auroit
    -0.54
     beliau
    -0.53
     étoit
    -0.52
     feroit
    -0.52
     faveur
    -0.50
     Empfehlungen
    -0.50
     ję
    -0.47
     Comentarios
    -0.46
     jengibre
    -0.46
    POSITIVE LOGITS
     underground
    1.20
     Underground
    1.10
    Underground
    1.09
    underground
    1.02
     subterranean
    0.88
     underwater
    0.72
     subsurface
    0.68
    地下
    0.68
     subter
    0.67
     subterrá
    0.63
    Act Density 0.008%

    No Known Activations