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

    Neuronpedia

    INDEX
    Explanations

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bearings
    -0.07
    -dot
    -0.07
     Orig
    -0.06
     Becker
    -0.06
     marked
    -0.06
     chaired
    -0.06
     wooden
    -0.06
    143
    -0.06
     thinks
    -0.06
     figured
    -0.06
    POSITIVE LOGITS
     release
    0.12
     Release
    0.10
     releases
    0.10
     released
    0.10
    _RELEASE
    0.10
    release
    0.09
    _Release
    0.08
    BP
    0.08
    Release
    0.08
    CS
    0.08
    Act Density 0.027%

    No Known Activations