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

    Neuronpedia

    INDEX
    Explanations

    access modifiers related to methods and classes in programming code

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

    protect/protected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jesteśmy
    -0.37
    ferenz
    -0.37
     estamos
    -0.36
    liyor
    -0.36
     chrétiens
    -0.35
     AssemblyProduct
    -0.34
     theyre
    -0.33
    ffeine
    -0.33
     ucapnya
    -0.32
    Bali
    -0.31
    POSITIVE LOGITS
    protected
    2.73
     protected
    2.25
    Protected
    1.95
     Protected
    1.95
     PROTECT
    1.50
     protegido
    1.50
    protect
    1.39
     protection
    1.38
    protection
    1.37
    PROTECT
    1.36
    Act Density 0.002%

    No Known Activations