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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     答
    -0.08
     closed
    -0.07
    选
    -0.06
     Life
    -0.06
     residence
    -0.06
    apel
    -0.06
    	sql
    -0.06
     MIL
    -0.06
     Epstein
    -0.06
    yers
    -0.06
    POSITIVE LOGITS
     latter
    0.07
     السم
    0.06
    (br
    0.06
     "..
    0.06
    DDR
    0.06
    -remove
    0.06
     �
    0.06
    嘛
    0.06
     Basic
    0.06
     legitimately
    0.06
    Act Density 0.016%

    No Known Activations