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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TRA
    -0.07
     --
    -0.06
     poměr
    -0.06
    eus
    -0.06
    thal
    -0.06
     duro
    -0.06
    =float
    -0.06
    σον
    -0.06
    ･･
    -0.05
    IDO
    -0.05
    POSITIVE LOGITS
    ammu
    0.07
    .doc
    0.07
    oving
    0.07
    없는
    0.07
    é
    0.07
    Uniform
    0.06
    traction
    0.06
    phabet
    0.06
     Canvas
    0.06
    ))))↵
    0.06
    Act Density 0.074%

    No Known Activations