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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ула
    -0.07
    imeters
    -0.06
     　　　　　
    -0.06
     batteries
    -0.06
    sequences
    -0.06
     focusing
    -0.06
     declined
    -0.06
     влас
    -0.06
    Generally
    -0.06
    Syn
    -0.06
    POSITIVE LOGITS
    xlsx
    0.07
    τών
    0.07
    틀
    0.06
    /St
    0.06
    ि�
    0.06
    sono
    0.06
    젝
    0.06
    сим
    0.06
     зн
    0.06
    ping
    0.06
    Act Density 0.101%

    No Known Activations