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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     روش
    -0.07
     된
    -0.07
    また
    -0.06
     текст
    -0.06
     dette
    -0.06
    -final
    -0.06
    _PREFIX
    -0.06
     Волод
    -0.06
     homem
    -0.06
    卓
    -0.06
    POSITIVE LOGITS
    chester
    0.07
     disrupted
    0.06
     جا
    0.06
    .getInput
    0.06
     Premier
    0.06
     scrapped
    0.06
    IFICATE
    0.06
    prof
    0.06
    ?;↵
    0.06
    .***.***
    0.06
    Act Density 0.003%

    No Known Activations