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

    Neuronpedia

    INDEX
    Explanations

    js

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nevy
    -0.07
     Afghan
    -0.06
     yerleş
    -0.06
    )));
    -0.06
     Cooperative
    -0.06
    层
    -0.06
    	J
    -0.06
     zví
    -0.06
    ifact
    -0.06
    -through
    -0.06
    POSITIVE LOGITS
     explains
    0.07
     PER
    0.07
     खबर
    0.06
     sod
    0.06
    /to
    0.06
     password
    0.06
     mistr
    0.06
    tee
    0.06
    .dropout
    0.06
    (scroll
    0.06
    Act Density 0.000%

    No Known Activations