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

    Neuronpedia

    INDEX
    Explanations

    content related to caution and personal relationships

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

    after question words

    np_acts-logits-general · gemini-2.0-flash

    scandalous or critical commentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.64
    OGND
    -0.61
    zug
    -0.57
     fairly
    -0.56
    diat
    -0.55
     ExecuteAsync
    -0.54
    Thunk
    -0.54
     télécommande
    -0.54
     significantly
    -0.54
    Datuak
    -0.54
    POSITIVE LOGITS
    enetrable
    0.50
     personali
    0.49
     sleeping
    0.48
     impotent
    0.47
    شهاد
    0.47
     cursed
    0.47
     elected
    0.47
     illogical
    0.46
     GetComponent
    0.46
    üttel
    0.46
    Act Density 0.176%

    No Known Activations