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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لن
    -0.07
    adata
    -0.07
     Our
    -0.07
    όδ
    -0.06
    ここ
    -0.06
     karma
    -0.06
    Our
    -0.06
     Grades
    -0.06
     terrace
    -0.06
     leaked
    -0.06
    POSITIVE LOGITS
    .production
    0.07
     beyaz
    0.06
    нерг
    0.06
     INCLUDED
    0.06
     použit
    0.06
     salope
    0.06
    iterator
    0.06
                            ↵
    0.06
     đẹp
    0.06
    рос
    0.06
    Act Density 0.024%

    No Known Activations