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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occasionally
    -0.07
    uebas
    -0.07
     someday
    -0.06
    ощи
    -0.06
    ties
    -0.06
     히
    -0.06
     onclick
    -0.06
    select
    -0.06
    _minimum
    -0.06
    Interesting
    -0.06
    POSITIVE LOGITS
    ouse
    0.07
    what
    0.06
    風
    0.06
    309
    0.06
     right
    0.06
     GraphQL
    0.06
    					↵					↵
    0.06
     WHAT
    0.06
    ']),
    0.06
    129
    0.06
    Act Density 0.000%

    No Known Activations