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

    Neuronpedia

    INDEX
    Explanations

    Medical scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scrollbar
    -0.07
     پیوند
    -0.07
    weight
    -0.07
     DW
    -0.06
    قه
    -0.06
    후
    -0.06
    _alg
    -0.06
     Cardinals
    -0.06
     nip
    -0.06
     childcare
    -0.06
    POSITIVE LOGITS
    (theta
    0.07
    vůli
    0.07
    ียร
    0.06
    ?>"/>↵
    0.06
    海
    0.06
     Phú
    0.06
    ξι
    0.06
     Paso
    0.06
     <=>
    0.06
    ，也
    0.06
    Act Density 0.050%

    No Known Activations