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

    Neuronpedia

    INDEX
    Explanations

    differential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pounded
    -0.07
    .embedding
    -0.07
     mankind
    -0.06
    enheim
    -0.06
     measurement
    -0.06
    presso
    -0.06
    emm
    -0.06
     Nobody
    -0.06
     elapsed
    -0.06
     Vec
    -0.06
    POSITIVE LOGITS
     MPL
    0.08
    callable
    0.07
     minib
    0.07
    uff
    0.06
    SELF
    0.06
    _LOWER
    0.06
    _COMPLEX
    0.06
    'clock
    0.06
    Spaces
    0.06
    Delegate
    0.06
    Act Density 0.004%

    No Known Activations