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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    907
    -0.06
     فور
    -0.06
     Bern
    -0.06
     ceremon
    -0.06
     Cous
    -0.06
    алізації
    -0.06
     LOSS
    -0.06
     Zem
    -0.06
    istor
    -0.06
    Signed
    -0.06
    POSITIVE LOGITS
    .FONT
    0.07
    .Role
    0.07
     질문
    0.07
    declar
    0.07
    exports
    0.07
     Overflow
    0.06
    traction
    0.06
    PF
    0.06
     ');
↵
    0.06
     migrate
    0.06
    Act Density 0.000%

    No Known Activations