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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'B
    -0.07
    ERRQ
    -0.06
     læ
    -0.06
    xing
    -0.06
     incest
    -0.06
    rell
    -0.06
    song
    -0.06
     mxArray
    -0.06
     vending
    -0.06
    =pd
    -0.06
    POSITIVE LOGITS
    ogenerated
    0.08
     tighten
    0.08
    	Object
    0.07
     mother
    0.07
    TMP
    0.07
    Closure
    0.07
     LEN
    0.06
    Container
    0.06
     я
    0.06
    _NAMESPACE
    0.06
    Act Density 0.002%

    No Known Activations