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

    Neuronpedia

    INDEX
    Explanations

    median

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incorporation
    -0.07
     tinder
    -0.06
     assisted
    -0.06
     sex
    -0.06
     warmed
    -0.06
     отп
    -0.06
     его
    -0.06
     AMP
    -0.06
     Tome
    -0.06
    abcdefghijklmnop
    -0.06
    POSITIVE LOGITS
    ufficient
    0.07
     oblivious
    0.07
    食べ
    0.07
    ування
    0.07
    ển
    0.07
    Standing
    0.07
    .SQL
    0.07
    결
    0.06
    Conn
    0.06
    (SQLException
    0.06
    Act Density 0.000%

    No Known Activations