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

    Neuronpedia

    INDEX
    Explanations

    information related to drug assessment and toxicity testing methodologies

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

    predictive models for compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valg
    -0.29
    awarkan
    -0.29
    volezza
    -0.29
    ArgumentParser
    -0.28
    penup
    -0.27
    SupportActionBar
    -0.27
     acreditar
    -0.27
     Soft
    -0.27
     nozze
    -0.26
    vierten
    -0.26
    POSITIVE LOGITS
     zwiſchen
    0.70
     queſto
    0.69
    <unused28>
    0.68
    <unused41>
    0.68
    <unused8>
    0.68
    [@BOS@]
    0.68
    <unused42>
    0.68
    <unused43>
    0.68
    <unused16>
    0.68
    <unused3>
    0.68
    Act Density 0.187%

    No Known Activations