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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cel
    -0.07
    �
    -0.06
    551
    -0.06
     calls
    -0.06
    ذر
    -0.06
    	utils
    -0.06
    128
    -0.06
    Procedure
    -0.06
     content
    -0.06
    091
    -0.06
    POSITIVE LOGITS
    estate
    0.07
     wonderful
    0.06
    es
    0.06
     Orth
    0.06
    }';↵
    0.06
    unkt
    0.06
    �n
    0.06
     ic
    0.06
    іття
    0.06
     ";↵↵
    0.06
    Act Density 0.012%

    No Known Activations