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

    Neuronpedia

    INDEX
    Explanations

    instances of past tense verbs or completed actions

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

    expressing communication and inquiry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.58
    InputBorder
    -0.51
    Rptr
    -0.43
    دانشنامهٔ
    -0.42
    vician
    -0.41
    ooplankton
    -0.41
     IFTT
    -0.40
    -0.40
    hamdulillah
    -0.40
     kasarigan
    -0.39
    POSITIVE LOGITS
     talking
    0.97
    talking
    0.84
     discussing
    0.75
    Talking
    0.72
     Talking
    0.71
     chatting
    0.70
     hablando
    0.66
     saying
    0.62
     telling
    0.61
     conversation
    0.58
    Act Density 0.078%

    No Known Activations