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

    Neuronpedia

    INDEX
    Explanations

    academic research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gro
    -0.07
    Jackson
    -0.06
    ЕС
    -0.06
     Electric
    -0.06
    :checked
    -0.06
    	rb
    -0.06
     Tobacco
    -0.06
     lif
    -0.06
    dbh
    -0.06
     Como
    -0.06
    POSITIVE LOGITS
    Bid
    0.07
    업
    0.07
     nodded
    0.06
     환산
    0.06
    INU
    0.06
     [...
    0.06
    .Signal
    0.06
    rika
    0.06
    ±ظ
    0.06
    .Container
    0.06
    Act Density 0.078%

    No Known Activations