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

    Neuronpedia

    INDEX
    Explanations

    .getText

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昼夜
    -0.08
    енных
    -0.07
    ⛧
    -0.07
    ﯨ
    -0.07
     Inch
    -0.07
    ductory
    -0.07
    𝙼
    -0.07
    钏
    -0.06
    𬶟
    -0.06
    ↡
    -0.06
    POSITIVE LOGITS
     Roberts
    0.07
    kos
    0.07
    _parent
    0.07
     gy
    0.07
    ereg
    0.07
     egy
    0.07
     Rogers
    0.07
    TOOLS
    0.07
    berger
    0.06
     stray
    0.06
    Act Density 0.003%

    No Known Activations