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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .span
    -0.08
     electrical
    -0.08
     Spann
    -0.08
    .width
    -0.08
     lattice
    -0.07
     विद्य
    -0.07
    \t
    -0.07
     SWITCH
    -0.07
     span
    -0.07
     spac
    -0.07
    POSITIVE LOGITS
     sympathique
    0.11
     complac
    0.10
    ’aa
    0.09
    qab
    0.09
    thinking
    0.09
    getwijfeld
    0.09
    түстік
    0.09
     denkt
    0.09
     sekal
    0.09
     zufrieden
    0.09
    Act Density 0.008%

    No Known Activations