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

    Neuronpedia

    INDEX
    Explanations

    Technical text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interpreter
    -0.07
    gambar
    -0.07
    regar
    -0.06
     enormously
    -0.06
    ickle
    -0.06
    براير
    -0.06
    reator
    -0.06
    Utilities
    -0.06
     zw
    -0.06
    ital
    -0.06
    POSITIVE LOGITS
    family
    0.07
     enjoyed
    0.07
     announcements
    0.06
     deze
    0.06
    .firstName
    0.06
     freedom
    0.06
     다음
    0.06
     ApplicationException
    0.06
    (fileName
    0.06
     "%"
    0.06
    Act Density 0.106%

    No Known Activations