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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with formal studies and organizations

    oai_token-act-pair · gemini-2.0-flash

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gleiche
    -0.59
     exercises
    -0.58
    SpringBootTest
    -0.56
     المعرف
    -0.53
    rovnik
    -0.53
    InitVars
    -0.53
     attendu
    -0.52
     cię
    -0.52
    xffffffff
    -0.50
     learnings
    -0.50
    POSITIVE LOGITS
     विश्वसनीयता
    0.57
    脚注の使い方
    0.51
    ConstraintMaker
    0.47
    ∎
    0.46
    первых
    0.46
    Ini
    0.45
    ナメント
    0.45
    lds
    0.45
     dép
    0.44
     estekak
    0.44
    Act Density 1.517%

    No Known Activations