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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devant
    -0.06
    Extreme
    -0.06
     здоб
    -0.06
    closure
    -0.06
     нен
    -0.06
    UND
    -0.06
    arto
    -0.06
    cash
    -0.06
    �
    -0.06
    -corner
    -0.06
    POSITIVE LOGITS
     */↵↵↵
    0.07
     gamb
    0.07
     Equ
    0.07
     quadr
    0.07
     Vet
    0.06
     gia
    0.06
    یستم
    0.06
     З
    0.06
     pwm
    0.06
    odied
    0.06
    Act Density 0.000%

    No Known Activations