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

    Neuronpedia

    INDEX
    Explanations

    thesize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chatter
    -0.08
    /color
    -0.07
     eher
    -0.06
     ông
    -0.06
    enga
    -0.06
     flowed
    -0.06
    illis
    -0.06
     u
    -0.06
    'O
    -0.06
    &P
    -0.06
    POSITIVE LOGITS
     brought
    0.07
    DEX
    0.06
     diarrhea
    0.06
    DAO
    0.06
    Gift
    0.06
    گرد
    0.06
    /*↵
    0.06
    .Company
    0.06
    ":{↵
    0.06
    .isAdmin
    0.06
    Act Density 0.015%

    No Known Activations