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

    Neuronpedia

    INDEX
    Explanations

    duplex communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olecules
    -0.07
     solicit
    -0.07
     ASN
    -0.06
    houses
    -0.06
    ात
    -0.06
    pol
    -0.06
    cut
    -0.06
    President
    -0.06
    itives
    -0.06
     ECM
    -0.06
    POSITIVE LOGITS
    ahaha
    0.07
     дос
    0.07
    .messaging
    0.07
     mentality
    0.06
     trillion
    0.06
    odzi
    0.06
     dile
    0.06
    .SetString
    0.06
    σιμοποι
    0.06
    crap
    0.06
    Act Density 0.006%

    No Known Activations