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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical procedures and patient management

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

    safety, permission, or allowance

    np_acts-logits-general · gemini-2.0-flash

    safety and permissibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jefus
    -0.76
     $_"
    -0.74
     Monfieur
    -0.70
     itſelf
    -0.70
     Efq
    -0.69
     IBOutlet
    -0.66
     myſelf
    -0.66
     Diſ
    -0.65
    ContentAsync
    -0.64
     raiſ
    -0.63
    POSITIVE LOGITS
     safe
    1.07
     safely
    0.96
     permitted
    0.91
     permissible
    0.88
     suitability
    0.85
     allowable
    0.84
    safe
    0.82
     OK
    0.81
     permission
    0.79
     safest
    0.78
    Act Density 0.473%

    No Known Activations