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

    Neuronpedia

    INDEX
    Explanations

    receiving confirmations or invitations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AUT
    -0.07
     beach
    -0.06
    enin
    -0.06
    pled
    -0.06
    /avatar
    -0.06
    illator
    -0.06
     BER
    -0.06
    ANS
    -0.06
    IPPING
    -0.06
    partners
    -0.06
    POSITIVE LOGITS
    [J
    0.06
    )){
↵
    0.06
     بلکه
    0.06
    OrderBy
    0.06
    _nan
    0.06
    "/
    0.06
    preserve
    0.06
     {↵
    0.06
     FullName
    0.05
     Surgical
    0.05
    Act Density 0.061%

    No Known Activations