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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ngh
    -0.06
    799
    -0.06
     poem
    -0.06
    INI
    -0.06
     mín
    -0.06
     benef
    -0.06
     iVar
    -0.06
     FM
    -0.06
    Selectors
    -0.06
    \Traits
    -0.06
    POSITIVE LOGITS
    風
    0.07
    "/>↵↵
    0.07
    alement
    0.06
    _extended
    0.06
    >('
    0.06
    always
    0.06
    transport
    0.06
     достат
    0.06
    .advance
    0.06
    ften
    0.06
    Act Density 0.004%

    No Known Activations