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

    Neuronpedia

    INDEX
    Explanations

    mentions of challenges and the possibility of overcoming them

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

    impossibility and unlikelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urlpatterns
    -0.43
     disambiguazione
    -0.40
    Aiheesta
    -0.36
     äl
    -0.35
    rungsseite
    -0.35
     الحره
    -0.35
     insuffisamment
    -0.35
     grises
    -0.35
     otomatig
    -0.35
    fjspx
    -0.35
    POSITIVE LOGITS
    impossible
    0.71
     impossible
    0.67
    Impossible
    0.63
     impossibile
    0.58
     unrealistic
    0.57
     Impossible
    0.56
    RegressionTest
    0.55
    ConstraintMaker
    0.53
     sogni
    0.51
     imposible
    0.51
    Act Density 0.066%

    No Known Activations