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

    Neuronpedia

    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "nil
    -0.07
     crisp
    -0.07
    肩负
    -0.07
     Herc
    -0.07
    vj
    -0.06
    DOB
    -0.06
    험
    -0.06
    <Test
    -0.06
    scient
    -0.06
    ]bool
    -0.06
    POSITIVE LOGITS
     leading
    0.07
    .Buttons
    0.07
    ession
    0.07
    Tuesday
    0.07
    :bg
    0.07
    ƪ
    0.07
     lexer
    0.07
    	loop
    0.06
    闰
    0.06
    ----------------
    0.06
    Act Density 0.000%

    No Known Activations