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

    Neuronpedia

    INDEX
    Explanations

    thief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旰
    -0.07
    湛江
    -0.07
    setValue
    -0.07
     Consultant
    -0.06
    北海
    -0.06
     UC
    -0.06
    .inc
    -0.06
     =&
    -0.06
     typingsSlinky
    -0.06
     масло
    -0.06
    POSITIVE LOGITS
     wheel
    0.08
    illow
    0.07
    𝕛
    0.07
    дж
    0.07
    hma
    0.06
    _temperature
    0.06
    тики
    0.06
    �
    0.06
     Specifications
    0.06
    _DEAD
    0.06
    Act Density 0.007%

    No Known Activations