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

    Neuronpedia

    INDEX
    Explanations

    requirement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    共
    -0.06
     linked
    -0.06
     tips
    -0.06
    .blob
    -0.06
    comfort
    -0.06
    这
    -0.06
     lecturer
    -0.06
    �
    -0.06
     graphics
    -0.06
    azar
    -0.06
    POSITIVE LOGITS
     Buckingham
    0.07
     vybav
    0.07
     lys
    0.06
     پن
    0.06
    PEND
    0.06
     Flem
    0.06
    oom
    0.06
    urum
    0.06
    سين
    0.06
    ้องน
    0.06
    Act Density 0.005%

    No Known Activations