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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irmingham
    -0.07
     shortcode
    -0.07
     superintendent
    -0.07
    に見
    -0.07
    —"
    -0.07
     //----------------
    -0.06
    .setColumns
    -0.06
    Dealer
    -0.06
     "
    -0.06
     authorised
    -0.06
    POSITIVE LOGITS
    "})↵
    0.07
     hỏi
    0.07
    '})↵
    0.06
    ัฒน
    0.06
     LH
    0.06
    __()↵
    0.06
    iphers
    0.06
    .second
    0.06
    ]])↵↵
    0.06
    logic
    0.06
    Act Density 0.060%

    No Known Activations