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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laser
    -0.07
     chassis
    -0.07
    CD
    -0.06
     PG
    -0.06
    IDENT
    -0.06
     salary
    -0.06
    友
    -0.06
     Sexy
    -0.06
     reass
    -0.06
    .Cancel
    -0.06
    POSITIVE LOGITS
     buna
    0.07
     अप
    0.07
    ={`/
    0.07
    /^
    0.06
    <Option
    0.06
     عم
    0.06
    |=
    0.06
     �
    0.06
    нять
    0.06
    ーネ
    0.06
    Act Density 0.002%

    No Known Activations