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

    Neuronpedia

    INDEX
    Explanations

    stable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /question
    -0.06
     implying
    -0.06
     compel
    -0.06
    АН
    -0.06
     filmmakers
    -0.06
    ará
    -0.06
    asan
    -0.06
    IllegalArgumentException
    -0.06
    ehen
    -0.06
    eh
    -0.06
    POSITIVE LOGITS
     stable
    0.14
     Stable
    0.09
     unstable
    0.09
    稳
    0.09
     stabilize
    0.09
     instability
    0.08
     stability
    0.07
     एड
    0.07
     плав
    0.07
     distur
    0.06
    Act Density 0.015%

    No Known Activations