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
    317
    -0.07
    (fm
    -0.07
     deviation
    -0.07
     Pharma
    -0.06
     Ramos
    -0.06
    犯罪
    -0.06
     گرفتن
    -0.06
     +↵↵
    -0.06
     변화
    -0.06
    甜
    -0.06
    POSITIVE LOGITS
    (gcf
    0.08
     altitude
    0.07
    στ
    0.07
    =output
    0.07
    :'',
    0.06
    _System
    0.06
    .container
    0.06
    phones
    0.06
     форме
    0.06
    wią
    0.06
    Act Density 0.001%

    No Known Activations