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

    Neuronpedia

    INDEX
    Explanations

    technology, security, economics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ocean
    -0.07
     agr
    -0.06
    Ascii
    -0.06
    &a
    -0.06
    grand
    -0.06
    requirements
    -0.06
    hello
    -0.06
    .phi
    -0.06
    ινε
    -0.06
     remainder
    -0.06
    POSITIVE LOGITS
    wards
    0.07
     mik
    0.07
    kop
    0.07
     Johnny
    0.07
    Johnny
    0.06
     leben
    0.06
     Jets
    0.06
    .'"↵↵
    0.06
    /legal
    0.06
     Jonathan
    0.06
    Act Density 0.206%

    No Known Activations