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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pag
    -0.06
     Hundred
    -0.06
     tablesp
    -0.06
    Cad
    -0.06
    ugar
    -0.06
     zł
    -0.06
    Constructed
    -0.06
    학기
    -0.06
    .grade
    -0.06
    bond
    -0.06
    POSITIVE LOGITS
    ative
    0.07
     diye
    0.07
    BUTTONDOWN
    0.07
     TRANSACTION
    0.06
    affe
    0.06
     cedar
    0.06
    ailure
    0.06
    単
    0.06
     Creative
    0.06
     Sitting
    0.06
    Act Density 0.008%

    No Known Activations