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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Continuous
    -0.07
    .bt
    -0.07
     speaking
    -0.06
     Seal
    -0.06
     repetition
    -0.06
     definition
    -0.06
     สถาน
    -0.06
     hypocrisy
    -0.06
    quoted
    -0.06
     praised
    -0.06
    POSITIVE LOGITS
    okia
    0.07
    txn
    0.07
    GMEM
    0.06
     sigh
    0.06
    TN
    0.06
    �
    0.06
    щество
    0.06
    ına
    0.06
    .LoadScene
    0.06
     Luckily
    0.06
    Act Density 0.009%

    No Known Activations