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

    Neuronpedia

    INDEX
    Explanations

    correspond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biome
    -0.07
    �
    -0.07
    alan
    -0.07
     facilit
    -0.06
     infusion
    -0.06
     '*
    -0.06
    inct
    -0.06
     Fuck
    -0.06
     Rating
    -0.06
    	boost
    -0.06
    POSITIVE LOGITS
     corresponding
    0.10
     correspond
    0.10
     corresponds
    0.10
     Comparable
    0.07
    ného
    0.07
     odp
    0.07
    ///↵
    0.07
    ические
    0.07
    aincontri
    0.07
     correspondence
    0.07
    Act Density 0.014%

    No Known Activations