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

    Neuronpedia

    INDEX
    Explanations

    uses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thải
    -0.07
    ・ア
    -0.06
     palate
    -0.06
    ména
    -0.06
    HP
    -0.06
     contract
    -0.06
    simulation
    -0.06
     relating
    -0.06
    eating
    -0.06
     Acting
    -0.06
    POSITIVE LOGITS
    　　　　　　　　　　　　　　
    0.07
    .spark
    0.07
     NATO
    0.06
    _REPLY
    0.06
     Gur
    0.06
     Pear
    0.06
    okia
    0.06
    咲
    0.06
     Short
    0.06
     MID
    0.06
    Act Density 0.517%

    No Known Activations