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

    Neuronpedia

    INDEX
    Explanations

    US

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ø
    -0.09
    istrator
    -0.07
    ♡
    -0.07
     minced
    -0.06
     Lumpur
    -0.06
    tank
    -0.06
    JR
    -0.06
    aleza
    -0.06
    ditor
    -0.06
    коном
    -0.06
    POSITIVE LOGITS
     spread
    0.07
    arf
    0.06
     develops
    0.06
     Nebraska
    0.06
     creators
    0.06
     Brazil
    0.06
    �
    0.06
     Electric
    0.06
     arithmetic
    0.06
     Appeals
    0.06
    Act Density 0.049%

    No Known Activations