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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     двиг
    -0.07
    ��
    -0.07
    strain
    -0.06
    orrh
    -0.06
    buie
    -0.06
    >Your
    -0.06
     shuffled
    -0.06
    $m
    -0.06
    зем
    -0.06
     просто
    -0.06
    POSITIVE LOGITS
     &'
    0.07
    Reviewed
    0.07
     [+
    0.06
     {\↵
    0.06
    LAG
    0.06
     eigen
    0.06
    icontains
    0.06
    /art
    0.06
     ]
    0.06
    Wave
    0.06
    Act Density 0.000%

    No Known Activations