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

    Neuronpedia

    INDEX
    Explanations

    files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sanctuary
    -0.07
     DPS
    -0.06
    gram
    -0.06
    <N
    -0.06
     consist
    -0.06
     Assistance
    -0.06
    Documents
    -0.06
     ranked
    -0.06
     ambit
    -0.06
     quit
    -0.06
    POSITIVE LOGITS
    ENOMEM
    0.07
     acesso
    0.07
    elder
    0.07
     Tablets
    0.07
    iele
    0.07
    [Byte
    0.07
    ._↵↵
    0.07
    .findIndex
    0.06
     MV
    0.06
    unft
    0.06
    Act Density 0.000%

    No Known Activations