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

    Neuronpedia

    INDEX
    Explanations

    basal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    choice
    -0.07
    	effect
    -0.07
    refund
    -0.07
     Laurie
    -0.07
    檢
    -0.07
    ิทธ
    -0.06
     pelic
    -0.06
     Те
    -0.06
     edt
    -0.06
     trainers
    -0.06
    POSITIVE LOGITS
     basal
    0.14
    asal
    0.08
    al
    0.07
     Bod
    0.07
     Gaw
    0.07
     WAL
    0.07
    642
    0.06
     broad
    0.06
    AL
    0.06
    ossil
    0.06
    Act Density 0.001%

    No Known Activations