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

    Neuronpedia

    INDEX
    Explanations

    language related to crimes involving victims

    oai_token-act-pair · gemini-2.0-flash

    victim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     victim
    -2.47
     victims
    -2.39
     Victims
    -2.06
    victim
    -2.06
     Victim
    -2.05
     victimes
    -1.97
     victime
    -1.94
    Victim
    -1.91
     víctima
    -1.81
     víctimas
    -1.69
    POSITIVE LOGITS
     ?>>
    0.71
    awtextra
    0.67
    StoryboardSegue
    0.66
     initComponents
    0.66
    PhysRevLett
    0.59
    ütün
    0.58
    Nuorodos
    0.58
    TestingModule
    0.58
     تانيه
    0.56
    }],
    0.56
    Act Density 5.999%

    No Known Activations