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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Connecting
    -0.07
    NETWORK
    -0.06
    /error
    -0.06
    ↑
    -0.06
    /interface
    -0.06
     функци
    -0.06
     Spartan
    -0.06
     school
    -0.06
     而
    -0.06
    <K
    -0.06
    POSITIVE LOGITS
    until
    0.07
    phis
    0.06
    Regardless
    0.06
    relation
    0.06
     Tham
    0.06
    invoice
    0.06
    ��
    0.06
    uye
    0.06
    ілі
    0.06
     puede
    0.06
    Act Density 0.133%

    No Known Activations