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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liberated
    -0.07
     Stanford
    -0.07
    лося
    -0.07
    React
    -0.07
    +:
    -0.07
    /N
    -0.07
     planning
    -0.06
     Moh
    -0.06
     frustr
    -0.06
    BU
    -0.06
    POSITIVE LOGITS
    _ENCOD
    0.06
    IRMWARE
    0.06
     záznam
    0.06
    体育
    0.06
    اتی
    0.06
    INA
    0.06
     hled
    0.06
    .setViewport
    0.06
     ints
    0.06
    _diag
    0.06
    Act Density 0.060%

    No Known Activations