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

    Neuronpedia

    INDEX
    Explanations

    instances of rumors and discussions surrounding them

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

    rumors being discussed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tig
    -0.47
     PSS
    -0.44
     Prest
    -0.43
     Giving
    -0.42
    WC
    -0.41
    Give
    -0.41
     Cly
    -0.41
    LC
    -0.41
     pare
    -0.41
     frontal
    -0.40
    POSITIVE LOGITS
     rumors
    1.13
     rumor
    1.10
     rumour
    1.05
     rumours
    1.04
     Rumors
    0.97
    Rumors
    0.92
     rumores
    0.89
     незавершена
    0.79
     rumored
    0.77
     Wikiseite
    0.75
    Act Density 0.004%

    No Known Activations