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

    Neuronpedia

    INDEX
    Explanations

    math and programming symbols

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.87
    IntoConstraints
    -0.84
    AnimationsModule
    -0.83
     незавершена
    -0.79
    fjspx
    -0.78
     ſhe
    -0.73
    protoimpl
    -0.73
    etheless
    -0.70
    SpringRunner
    -0.70
     Efq
    -0.69
    POSITIVE LOGITS
    ("$.
    0.45
    orex
    0.42
    بیر
    0.41
    aggi
    0.41
    lit
    0.41
    isse
    0.41
    道路
    0.40
    ren
    0.40
    gs
    0.40
     sepak
    0.40
    Act Density 0.390%

    No Known Activations