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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wides
    -0.07
     dome
    -0.06
     verw
    -0.06
     fre
    -0.06
     behaves
    -0.06
    .top
    -0.06
     civ
    -0.06
     dan
    -0.06
     TPM
    -0.06
     Rew
    -0.06
    POSITIVE LOGITS
    _MPI
    0.07
    领
    0.06
    lovak
    0.06
     fromDate
    0.06
    _ABC
    0.06
    operations
    0.06
    Runnable
    0.06
    Advisor
    0.06
    heard
    0.06
     tactics
    0.06
    Act Density 0.022%

    No Known Activations