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

    Neuronpedia

    INDEX
    Explanations

    suppose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ocean
    -0.07
    FSIZE
    -0.07
     Little
    -0.07
     lead
    -0.07
    Nuitka
    -0.07
    Kids
    -0.07
     therein
    -0.06
     جریان
    -0.06
     FileSystem
    -0.06
     Ethernet
    -0.06
    POSITIVE LOGITS
     supreme
    0.08
     Supervisor
    0.08
     sup
    0.08
    sup
    0.08
     Supreme
    0.08
    Sup
    0.08
     supervisor
    0.08
    .Sup
    0.07
    trl
    0.07
     supervisors
    0.07
    Act Density 0.045%

    No Known Activations