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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Successfully
    -0.06
    anners
    -0.06
    дается
    -0.06
    Metadata
    -0.06
     If
    -0.06
    Rs
    -0.06
     The
    -0.06
    pron
    -0.06
    меч
    -0.06
    977
    -0.06
    POSITIVE LOGITS
     alph
    0.07
    .itemView
    0.07
     NCAA
    0.06
     tablet
    0.06
     yazar
    0.06
    :{
↵
    0.06
    RuntimeObject
    0.06
    료
    0.06
    ()↵↵↵
    0.06
    __((
    0.06
    Act Density 0.538%

    No Known Activations