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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แน
    -0.07
     Allows
    -0.07
     Hungary
    -0.06
     knows
    -0.06
    “How
    -0.06
     WB
    -0.06
    undry
    -0.06
    �
    -0.06
     تور
    -0.06
     Officials
    -0.06
    POSITIVE LOGITS
     %.
    0.06
     -:-
    0.06
    .display
    0.06
    -spec
    0.06
    -play
    0.06
     dk
    0.06
     خویش
    0.06
     output
    0.06
    )=>
    0.06
     on
    0.06
    Act Density 0.106%

    No Known Activations