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

    Neuronpedia

    INDEX
    Explanations

    work in process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formidable
    -0.07
    aced
    -0.07
     vetted
    -0.07
     effortless
    -0.07
    _ops
    -0.07
     verified
    -0.07
    stellen
    -0.07
     tạo
    -0.07
     opp
    -0.07
     ज़
    -0.07
    POSITIVE LOGITS
    irlpool
    0.09
     经
    0.08
    processing
    0.08
    ipient
    0.08
     消
    0.08
    _Device
    0.08
     bach
    0.08
     Reservoir
    0.08
     个
    0.08
     устройства
    0.08
    Act Density 0.001%

    No Known Activations