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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Razor
    -0.07
     thế
    -0.07
    Type
    -0.07
     Adam
    -0.06
     kolem
    -0.06
    odon
    -0.06
     tới
    -0.06
     maternity
    -0.06
     gol
    -0.06
     attendant
    -0.06
    POSITIVE LOGITS
     pohy
    0.06
    .PREFERRED
    0.06
     prolet
    0.06
     microbi
    0.06
     осві
    0.06
    things
    0.06
    تماد
    0.06
    �
    0.06
     aquí
    0.06
    underline
    0.06
    Act Density 0.058%

    No Known Activations