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

    Neuronpedia

    INDEX
    Explanations

    the presence and characteristics of prisons and prisoners

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

    prison

    np_acts-logits-general · gemini-2.0-flash

    prison security administration population

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.48
    LayoutInflater
    -0.42
     Desarrollo
    -0.40
     Haley
    -0.40
    stylers
    -0.40
    parency
    -0.39
     alfombra
    -0.39
     bemerken
    -0.39
    solicited
    -0.39
    PCA
    -0.38
    POSITIVE LOGITS
     prison
    1.84
     Prison
    1.71
    Prison
    1.55
    prison
    1.55
     PRISON
    1.52
     jail
    1.49
     prisons
    1.45
     Prisons
    1.40
     Jail
    1.30
     prisión
    1.30
    Act Density 0.358%

    No Known Activations