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

    Neuronpedia

    INDEX
    Explanations

    mathematical theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ોખ
    -0.09
     dictionaries
    -0.08
    운
    -0.08
     Morgan
    -0.07
    Chain
    -0.07
     phổ
    -0.07
    码
    -0.07
    ਾ�
    -0.07
     Chain
    -0.07
    益
    -0.07
    POSITIVE LOGITS
     കൊവിഡ്
    0.08
     նկ
    0.08
     ეტ
    0.08
     organic
    0.08
     წევ
    0.08
    ullugit
    0.08
    ørdag
    0.08
    除此
    0.08
    paamik
    0.08
     պատ
    0.08
    Act Density 0.008%

    No Known Activations