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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crown
    -0.06
     χρή
    -0.06
    onet
    -0.06
     headlines
    -0.06
     İtalya
    -0.06
     Sage
    -0.06
     fac
    -0.06
     Clair
    -0.06
    splash
    -0.05
    ierce
    -0.05
    POSITIVE LOGITS
    metadata
    0.07
    ční
    0.07
     обличчя
    0.07
    BufferData
    0.07
     outras
    0.07
    _ABI
    0.06
     erotisch
    0.06
     директор
    0.06
     vě
    0.06
     %%
    0.06
    Act Density 0.002%

    No Known Activations