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

    Neuronpedia

    INDEX
    Explanations

    mutant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    폭
    -0.07
    epar
    -0.07
     Virtual
    -0.07
     virtual
    -0.07
    Iteration
    -0.07
    代理
    -0.06
    quarters
    -0.06
     Elastic
    -0.06
    رب
    -0.06
    (return
    -0.06
    POSITIVE LOGITS
    іно
    0.07
     iss
    0.07
     throat
    0.06
     ماد
    0.06
     pact
    0.06
     Anatomy
    0.06
     casual
    0.06
     Rams
    0.06
    Father
    0.06
    union
    0.06
    Act Density 0.010%

    No Known Activations