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

    Neuronpedia

    INDEX
    Explanations

    statistical significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shining
    -0.07
    %n
    -0.07
    \Log
    -0.06
    阿
    -0.06
     μαζί
    -0.06
    -legged
    -0.06
    ^-
    -0.06
    _auth
    -0.06
    	rect
    -0.06
     showError
    -0.06
    POSITIVE LOGITS
     lax
    0.07
    yš
    0.07
     telecommunications
    0.07
     openly
    0.06
    Senate
    0.06
     Tie
    0.06
     Entrepreneur
    0.06
     kil
    0.06
     emanc
    0.06
     حذ
    0.06
    Act Density 0.011%

    No Known Activations