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

    Neuronpedia

    INDEX
    Explanations

    references to the impact or consequences of actions or substances

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

    effect on something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.56
     informée
    -0.55
     createSlice
    -0.55
     beginnetje
    -0.54
    numerusform
    -0.53
    parsedMessage
    -0.52
     queſta
    -0.52
     AssemblyCompany
    -0.52
     stiefe
    -0.52
    Demografie
    -0.51
    POSITIVE LOGITS
     effect
    0.60
     effects
    0.52
    Effect
    0.50
     Effect
    0.49
    effect
    0.47
    effetto
    0.42
     effets
    0.42
    Effects
    0.41
     etk
    0.41
     Effects
    0.41
    Act Density 0.184%

    No Known Activations