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

    Neuronpedia

    INDEX
    Explanations

    Job titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    msgs
    -0.06
    /Card
    -0.06
     quá
    -0.06
     된
    -0.06
    =subprocess
    -0.06
    retweeted
    -0.06
     z
    -0.06
    cept
    -0.06
     الق
    -0.06
     carpets
    -0.06
    POSITIVE LOGITS
     crush
    0.07
     území
    0.07
    rai
    0.06
     ode
    0.06
     crushing
    0.06
     ide
    0.06
    ardin
    0.06
     Din
    0.06
    ํ
    0.06
    الد
    0.06
    Act Density 0.037%

    No Known Activations