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

    Neuronpedia

    INDEX
    Explanations

    preliminary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lang
    -0.07
     attraction
    -0.07
    CAST
    -0.07
     Likely
    -0.06
     LL
    -0.06
     billionaires
    -0.06
    Seat
    -0.06
    ully
    -0.06
    ibus
    -0.06
     spouse
    -0.06
    POSITIVE LOGITS
     dejtings
    0.07
     kostenlos
    0.06
    '].$
    0.06
     �
    0.06
    -<?
    0.06
     cosmos
    0.06
     北
    0.06
     acquitted
    0.06
     ces
    0.06
     olmasına
    0.06
    Act Density 0.007%

    No Known Activations