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

    Neuronpedia

    INDEX
    Explanations

    grounded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dc
    -0.07
    784
    -0.07
     household
    -0.07
     buying
    -0.06
     traceback
    -0.06
    net
    -0.06
    '+
    -0.06
     ByteString
    -0.06
     treatment
    -0.06
     Urban
    -0.06
    POSITIVE LOGITS
    出した
    0.07
    atem
    0.06
     �
    0.06
     anchored
    0.06
    -step
    0.06
    面议
    0.06
    sometimes
    0.06
     mô
    0.06
    TestMethod
    0.06
     التش
    0.06
    Act Density 0.059%

    No Known Activations