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

    Neuronpedia

    INDEX
    Explanations

    say "itive" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incorrect
    -0.07
     chopped
    -0.07
     ordered
    -0.06
    _angle
    -0.06
     deform
    -0.06
     activities
    -0.06
    _money
    -0.06
     coupling
    -0.06
    HttpStatus
    -0.06
    chlor
    -0.06
    POSITIVE LOGITS
    黨
    0.07
     世
    0.07
     appellate
    0.07
    ogen
    0.06
    Exporter
    0.06
    ulty
    0.06
    	part
    0.06
     например
    0.06
     relação
    0.06
    .defaultProps
    0.06
    Act Density 0.004%

    No Known Activations