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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !:
    -0.06
     snad
    -0.06
     가장
    -0.06
     長
    -0.06
    	reader
    -0.06
     curse
    -0.06
    ář
    -0.06
     wielding
    -0.06
     bigint
    -0.06
     انگلیسی
    -0.06
    POSITIVE LOGITS
     established
    0.07
    /trunk
    0.07
    striction
    0.06
    `);↵
    0.06
    (',',$
    0.06
     establish
    0.06
    ("'
    0.06
    Sounds
    0.06
    _UID
    0.06
    ْع
    0.06
    Act Density 0.026%

    No Known Activations