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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wat
    -0.08
     били
    -0.08
     دائ
    -0.08
     мир
    -0.08
    ;b
    -0.08
    %'↵
    -0.08
    wat
    -0.08
    Rap
    -0.08
    orca
    -0.08
     Rap
    -0.07
    POSITIVE LOGITS
    (stage
    0.08
    chan
    0.07
     srand
    0.07
     Steiner
    0.07
    Chief
    0.07
     ingresso
    0.07
    Monte
    0.07
     Coordinator
    0.07
     Chief
    0.07
    897
    0.07
    Act Density 0.000%

    No Known Activations