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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fall
    -0.07
    ็จพระ
    -0.06
     aylık
    -0.06
    croll
    -0.06
     funded
    -0.06
    <Q
    -0.06
    ्वत
    -0.06
     pollution
    -0.06
    стре
    -0.06
     Engineer
    -0.06
    POSITIVE LOGITS
    	play
    0.08
    =n
    0.07
     lease
    0.07
    borrow
    0.06
    isp
    0.06
    )prepare
    0.06
    ebe
    0.06
     yapılan
    0.06
    unless
    0.06
    ++;
↵
    0.06
    Act Density 0.000%

    No Known Activations