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

    Neuronpedia

    INDEX
    Explanations

    terms related to sensitivity and specificity in analysis

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

    sensitivity analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JKLM
    -0.43
     république
    -0.42
     Fargo
    -0.39
     albo
    -0.37
     edilen
    -0.35
    berton
    -0.35
    zeuge
    -0.35
    Océ
    -0.34
     jotka
    -0.34
    pageX
    -0.34
    POSITIVE LOGITS
     sensitivity
    2.11
    Sensitivity
    1.98
     Sensitivity
    1.98
    sensitivity
    1.92
     sensitivities
    1.64
    ensitivity
    1.41
     sensibilité
    1.39
     sensibilidad
    1.35
     sensibility
    1.17
     sensi
    1.16
    Act Density 0.017%

    No Known Activations