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

    Neuronpedia

    INDEX
    Explanations

    written text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }$/
    -0.06
     frankfurt
    -0.06
     член
    -0.06
    CRE
    -0.06
     thickness
    -0.06
     Allan
    -0.06
    larının
    -0.06
     δη
    -0.06
    」と
    -0.06
    Dict
    -0.06
    POSITIVE LOGITS
     Cuisine
    0.07
     incredible
    0.07
    .Singleton
    0.07
     communicating
    0.07
     blackjack
    0.06
     cuisine
    0.06
     Additionally
    0.06
     missing
    0.06
    -threatening
    0.06
     Ellison
    0.06
    Act Density 0.000%

    No Known Activations