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

    Neuronpedia

    INDEX
    Explanations

    HTML "Prev Class"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    touches
    -0.07
     additional
    -0.06
     lake
    -0.06
    information
    -0.06
     lakes
    -0.06
     pedigree
    -0.06
    stří
    -0.06
     MI
    -0.06
     CR
    -0.06
    ци
    -0.06
    POSITIVE LOGITS
     rozum
    0.07
    pekt
    0.06
    |"
    0.06
     hiç
    0.06
    대표
    0.06
     ör
    0.06
    \""
    0.06
     "]"
    0.06
     sidew
    0.06
     nex
    0.06
    Act Density 0.005%

    No Known Activations