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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Giving
    -0.08
    larına
    -0.07
    erval
    -0.07
     言
    -0.06
     ước
    -0.06
     моз
    -0.06
    徒
    -0.06
    орон
    -0.06
    wife
    -0.06
     tarihli
    -0.06
    POSITIVE LOGITS
    ERRUPT
    0.07
     spectro
    0.06
    _PLACE
    0.06
     Surround
    0.06
     bamb
    0.06
     explicitly
    0.06
    {id
    0.06
    slide
    0.06
    energy
    0.06
     enchant
    0.06
    Act Density 0.297%

    No Known Activations