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

    Neuronpedia

    INDEX
    Explanations

    disposal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Linda
    -0.07
     hijos
    -0.07
    佩
    -0.07
    ете
    -0.06
    ceeded
    -0.06
    nehmer
    -0.06
    ören
    -0.06
    ingt
    -0.06
    pheric
    -0.06
    iddet
    -0.06
    POSITIVE LOGITS
     disposal
    0.16
    posal
    0.09
    WillDisappear
    0.08
    sur
    0.07
    Brazil
    0.07
    gb
    0.07
    Previous
    0.07
    extra
    0.07
    Extra
    0.07
     deportation
    0.07
    Act Density 0.003%

    No Known Activations