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

    Neuronpedia

    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     образ
    -0.07
     ObservableCollection
    -0.07
    Schedulers
    -0.06
    .repo
    -0.06
     geographic
    -0.06
     strncmp
    -0.06
    .Raycast
    -0.06
    قيق
    -0.06
     CES
    -0.06
    ."','".$
    -0.06
    POSITIVE LOGITS
     instruction
    0.07
    λά
    0.06
     fatto
    0.06
     possibly
    0.06
    ۀ
    0.06
     punishment
    0.06
    resse
    0.06
    -covered
    0.06
    PJ
    0.06
     reluctantly
    0.06
    Act Density 0.000%

    No Known Activations