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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ️
    -0.07
    ='.$
    -0.07
     paradise
    -0.06
     rk
    -0.06
    올
    -0.06
    Tok
    -0.06
     Бел
    -0.06
    outlined
    -0.06
     Anyway
    -0.06
     Vietnam
    -0.06
    POSITIVE LOGITS
     exemptions
    0.07
     unnecessarily
    0.07
    udes
    0.06
    :::::::::::
    0.06
    Phrase
    0.06
     vitam
    0.06
     DIRECT
    0.06
    フ�
    0.06
     indict
    0.06
     aggregated
    0.06
    Act Density 0.213%

    No Known Activations