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

    Neuronpedia

    INDEX
    Explanations

    Initial observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unately
    -0.07
    missions
    -0.06
    <hr
    -0.06
    icha
    -0.06
     comp
    -0.06
    溪
    -0.06
    pecial
    -0.06
     عدم
    -0.06
    енсив
    -0.05
    astle
    -0.05
    POSITIVE LOGITS
    _Draw
    0.07
     :/:
    0.07
    /devices
    0.07
     hdc
    0.07
    _rules
    0.07
     algebra
    0.07
    &)↵
    0.06
     yy
    0.06
    πισ
    0.06
     umb
    0.06
    Act Density 0.024%

    No Known Activations