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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    打卡
    -0.08
    /package
    -0.08
     inclus
    -0.07
    iveness
    -0.07
    link
    -0.07
    aval
    -0.07
     babes
    -0.07
     job
    -0.07
    还好
    -0.07
     lush
    -0.07
    POSITIVE LOGITS
    eating
    0.07
    #'
    0.07
     lcd
    0.06
     frog
    0.06
    最先
    0.06
    ührung
    0.06
    �
    0.06
    👌
    0.06
     violated
    0.06
     emphasizing
    0.06
    Act Density 0.004%

    No Known Activations