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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EXPECTED
    -0.07
    AUDIO
    -0.07
    .pointer
    -0.07
    èo
    -0.06
     vede
    -0.06
     difíc
    -0.06
    _component
    -0.06
    erras
    -0.06
     Blessed
    -0.06
    Cho
    -0.06
    POSITIVE LOGITS
    unit
    0.08
    یین
    0.07
     junit
    0.07
     NUnit
    0.07
    itin
    0.07
     outlier
    0.07
    pecially
    0.06
    units
    0.06
     slot
    0.06
    instr
    0.06
    Act Density 0.002%

    No Known Activations