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

    Neuronpedia

    INDEX
    Explanations

    String manipulation/character shifting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♤
    -0.08
    就在于
    -0.07
     eines
    -0.07
    想起了
    -0.07
     Bers
    -0.07
    weapons
    -0.07
    damn
    -0.07
    lements
    -0.07
    应该是
    -0.07
    依然是
    -0.06
    POSITIVE LOGITS
    ponsive
    0.07
     Floor
    0.07
    oline
    0.07
     Paperback
    0.07
     Equivalent
    0.07
    .priv
    0.07
     pprint
    0.07
     Sophie
    0.07
    ForKey
    0.07
    ello
    0.07
    Act Density 0.003%

    No Known Activations