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

    Neuronpedia

    INDEX
    Explanations

    mandatory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ildren
    -0.07
     평가
    -0.06
     cliff
    -0.06
    	delta
    -0.06
    Baş
    -0.06
     rời
    -0.06
     thesis
    -0.06
    nič
    -0.06
    됨
    -0.06
    ců
    -0.06
    POSITIVE LOGITS
    andatory
    0.09
     mandated
    0.09
     Mandatory
    0.08
    mentor
    0.07
     compulsory
    0.07
    mandatory
    0.07
    /mp
    0.06
     Norway
    0.06
    mong
    0.06
     determines
    0.06
    Act Density 0.010%

    No Known Activations