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

    Neuronpedia

    INDEX
    Explanations

    Horizontal formatting lines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izarre
    -0.08
     kos
    -0.08
    bum
    -0.08
     FK
    -0.08
     ngũ
    -0.07
     colourful
    -0.07
     histórico
    -0.07
     görd
    -0.07
     Verd
    -0.07
     charset
    -0.07
    POSITIVE LOGITS
     completeness
    0.07
    逐
    0.07
    應用
    0.07
     Investigation
    0.07
    /game
    0.07
     налог
    0.07
    合唱
    0.07
     Tale
    0.06
     Helping
    0.06
    时效
    0.06
    Act Density 0.003%

    No Known Activations