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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal immunity and corruption

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

    qualified immunity or police investigations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seamnă
    -0.42
    errHandler
    -0.42
    SerializedName
    -0.40
    complexType
    -0.39
     propOrder
    -0.39
    SequentialGroup
    -0.38
     unido
    -0.38
     embaraz
    -0.35
     actionMode
    -0.35
    enterOuterAlt
    -0.35
    POSITIVE LOGITS
     Police
    0.79
     POLICE
    0.77
    Police
    0.71
     police
    0.71
     policemen
    0.70
    police
    0.69
     policeman
    0.67
     Policing
    0.64
     cops
    0.60
     Detective
    0.60
    Act Density 0.543%

    No Known Activations