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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or titles of entities

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

    introducing specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étoit
    -0.47
     húmedo
    -0.42
     automático
    -0.38
     fédé
    -0.36
    +#+
    -0.35
     réve
    -0.35
     judiciaire
    -0.34
     pouvoit
    -0.34
     auroit
    -0.34
     solidaridad
    -0.34
    POSITIVE LOGITS
    parsedMessage
    0.77
    ConstraintMaker
    0.76
    цездатний
    0.74
    fjspx
    0.69
    GOTREF
    0.69
     resourceCulture
    0.69
     AssemblyProduct
    0.68
    RenderAtEndOf
    0.66
    Vidite
    0.65
    Datuak
    0.64
    Act Density 0.044%

    No Known Activations