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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     turbine
    -0.07
     kit
    -0.06
    definition
    -0.06
    TEXT
    -0.06
     vaccine
    -0.06
     Bol
    -0.06
     Sav
    -0.06
    unt
    -0.06
     Giant
    -0.06
     PIN
    -0.06
    POSITIVE LOGITS
    вропей
    0.07
    389
    0.07
    ání
    0.06
     einem
    0.06
    они
    0.06
     dialogRef
    0.06
     christian
    0.06
     brighter
    0.06
     Truy
    0.06
     Salary
    0.06
    Act Density 0.062%

    No Known Activations