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

    Neuronpedia

    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash

    The neuron lights up on words and contexts describing the use of force or coercion in sexual acts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    “What
    -0.07
    SENS
    -0.07
    　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　
    -0.06
     Pilot
    -0.06
    Prime
    -0.06
    "What
    -0.06
    :UITableView
    -0.06
    „V
    -0.06
    Retail
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     sins
    0.07
    vanced
    0.06
    riteln
    0.06
    ерж
    0.06
     tấm
    0.06
     Jamal
    0.06
     GraphQL
    0.06
     Bruins
    0.06
     концентра
    0.06
    �
    0.06
    Act Density 0.053%

    No Known Activations