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

    Neuronpedia

    INDEX
    Explanations

    If statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =plt
    -0.07
    ^K
    -0.07
    ン�
    -0.07
     Conse
    -0.07
    ánh
    -0.06
    做
    -0.06
    sticky
    -0.06
    ков
    -0.06
    .classes
    -0.06
     apellido
    -0.06
    POSITIVE LOGITS
     v
    0.06
     je
    0.06
    ('{
    0.06
     petroleum
    0.06
    €�
    0.06
    ↑
    0.06
     '');
    0.06
    learner
    0.06
    NM
    0.06
    hdl
    0.06
    Act Density 0.019%

    No Known Activations