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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or interactions involving movement or transfer

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

    music to my ears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adatta
    -0.44
    estias
    -0.39
     היתה
    -0.36
     africaine
    -0.35
    heiten
    -0.35
     soeur
    -0.35
    DNEY
    -0.35
     effetti
    -0.34
     ayrıca
    -0.34
     правда
    -0.33
    POSITIVE LOGITS
    InjectAttribute
    0.74
     surla
    0.69
     فريبيس
    0.52
    HideFlags
    0.52
    AnimationsModule
    0.52
    ⓧ
    0.50
     defaultstate
    0.50
    EndContext
    0.49
    ContentAlignment
    0.49
     informée
    0.48
    Act Density 0.033%

    No Known Activations