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

    Neuronpedia

    INDEX
    Explanations

    Scientific data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itas
    -0.07
    -power
    -0.07
    -going
    -0.07
    Expr
    -0.07
    =$
    -0.07
    -density
    -0.06
    袖
    -0.06
     Parcel
    -0.06
    -leg
    -0.06
    bservice
    -0.06
    POSITIVE LOGITS
     zal
    0.07
     Volt
    0.06
     أبريل
    0.06
    coli
    0.06
    (cont
    0.06
    ]!=
    0.06
     Bonus
    0.06
     necesita
    0.06
                                    ↵
    0.06
     inspirational
    0.06
    Act Density 0.043%

    No Known Activations