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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .core
    -0.07
     dict
    -0.07
    fatal
    -0.06
     unite
    -0.06
     speeches
    -0.06
    _resources
    -0.06
     Beans
    -0.06
    Present
    -0.06
     Wheels
    -0.06
    における
    -0.06
    POSITIVE LOGITS
     subsidiaries
    0.07
    &display
    0.06
     wat
    0.06
     çıkar
    0.06
    around
    0.06
     entrar
    0.06
    (gp
    0.06
     encaps
    0.06
     instructed
    0.06
    �재
    0.06
    Act Density 0.010%

    No Known Activations