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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reek
    -0.06
     valley
    -0.06
     edit
    -0.06
    �
    -0.06
     Either
    -0.06
    icit
    -0.06
    bx
    -0.06
     relieved
    -0.06
    	pool
    -0.06
     hủy
    -0.05
    POSITIVE LOGITS
    contres
    0.07
     lanz
    0.07
    :");↵
    0.07
    жение
    0.07
    .son
    0.07
     //----------------
    0.06
    .until
    0.06
    ')));↵
    0.06
    ẫ
    0.06
     Ρ
    0.06
    Act Density 0.002%

    No Known Activations