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

    Neuronpedia

    INDEX
    Explanations

    )dealloc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    úa
    -0.07
     beg
    -0.07
    ΙΝ
    -0.07
     Blair
    -0.07
    нар
    -0.07
    ject
    -0.07
     uuid
    -0.07
    ;'>
    -0.07
     lavoro
    -0.07
     proprio
    -0.06
    POSITIVE LOGITS
    щается
    0.07
    )dealloc
    0.06
    :max
    0.06
    Obviously
    0.06
     dealloc
    0.06
    discover
    0.06
    šší
    0.06
    dealloc
    0.06
    buffers
    0.06
    bsd
    0.06
    Act Density 0.001%

    No Known Activations