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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cao
    -0.07
    _pr
    -0.06
     above
    -0.06
    coeff
    -0.06
     Sentence
    -0.06
     induced
    -0.06
     realidad
    -0.06
     peasants
    -0.06
     IND
    -0.06
     temptation
    -0.06
    POSITIVE LOGITS
     αγ
    0.07
    アメリカ
    0.06
     paperwork
    0.06
    频次
    0.06
    vailability
    0.06
    科技
    0.06
    이비
    0.06
     breathtaking
    0.06
     workflows
    0.06
     Putin
    0.06
    Act Density 0.022%

    No Known Activations