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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ces
    -0.07
    .HE
    -0.07
     Drop
    -0.06
    _Settings
    -0.06
    isks
    -0.06
    Tony
    -0.06
    MH
    -0.06
    backup
    -0.06
    oston
    -0.06
    เว
    -0.06
    POSITIVE LOGITS
     cresc
    0.06
    -valu
    0.06
    /thread
    0.06
    ・
    0.06
    }}">{{$
    0.06
    astics
    0.06
    赏
    0.06
     професій
    0.06
    >);↵
    0.06
    ographics
    0.06
    Act Density 0.336%

    No Known Activations