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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     activism
    -0.07
     attitudes
    -0.07
    _phase
    -0.07
     types
    -0.07
     ži
    -0.06
    NECTION
    -0.06
     Disabled
    -0.06
     brokers
    -0.06
    出し
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    itelist
    0.06
    RESH
    0.06
    unky
    0.06
     SPD
    0.06
    κλη
    0.06
    CAPE
    0.06
    -Token
    0.06
    .tableView
    0.06
     clar
    0.06
    ={}↵
    0.06
    Act Density 0.018%

    No Known Activations