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

    Neuronpedia

    INDEX
    Explanations

    police reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     increasingly
    -0.06
    WA
    -0.06
     Entr
    -0.06
     Boxes
    -0.06
    絡
    -0.06
     Bron
    -0.06
     Trying
    -0.06
     piping
    -0.06
    _PLUS
    -0.05
    VAL
    -0.05
    POSITIVE LOGITS
     †
    0.08
    Aaron
    0.07
    íše
    0.07
    Submitted
    0.06
     nastav
    0.06
    uchs
    0.06
    .POST
    0.06
     Consumer
    0.06
    �
    0.06
     Chart
    0.06
    Act Density 0.030%

    No Known Activations