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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bow
    -0.07
    Rail
    -0.07
     grow
    -0.07
     wel
    -0.06
     Bullet
    -0.06
     مربع
    -0.06
     Rs
    -0.06
     Swimming
    -0.06
    .Track
    -0.06
     sürdür
    -0.06
    POSITIVE LOGITS
    HEMA
    0.07
    (props
    0.06
    anager
    0.06
    icky
    0.06
    ografie
    0.06
     userId
    0.06
     里
    0.06
    pective
    0.06
    ervice
    0.06
     Bounty
    0.06
    Act Density 0.000%

    No Known Activations