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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rido
    -0.07
    ât
    -0.06
    boa
    -0.06
    ούν
    -0.06
    .kr
    -0.06
    Kin
    -0.06
    emu
    -0.06
     travers
    -0.06
    Rich
    -0.06
    atta
    -0.06
    POSITIVE LOGITS
    ");
↵
    0.07
    _literals
    0.07
     Jewelry
    0.07
     Gov
    0.06
     Crow
    0.06
     addUser
    0.06
     DropDownList
    0.06
     Follow
    0.06
    ुध
    0.06
     参考
    0.06
    Act Density 0.098%

    No Known Activations