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

    Neuronpedia

    INDEX
    Explanations

    code and markup syntax

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.25
    -
    -0.87
    AsUp
    -0.58
    Noun
    -0.42
     deft
    -0.40
    ämän
    -0.40
    Tē
    -0.39
     [:
    -0.39
    orthy
    -0.39
     majd
    -0.38
    POSITIVE LOGITS
     utafitiHapana
    0.77
    herself
    0.72
    orghini
    0.71
    CloseOperation
    0.70
    makeConstraints
    0.69
    ADVERTISEMENT
    0.68
     auffi
    0.68
     themſelves
    0.68
    SequentialGroup
    0.68
    Архівовано
    0.67
    Act Density 3.896%

    No Known Activations