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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CTL
    -0.07
    parm
    -0.07
    ampus
    -0.07
    �
    -0.07
    话语
    -0.07
     شامل
    -0.07
    舐
    -0.07
    公认
    -0.07
    珙
    -0.07
     zob
    -0.07
    POSITIVE LOGITS
    repositories
    0.07
    🔻
    0.07
    )::
    0.07
     offers
    0.07
     France
    0.07
     royal
    0.07
     Securities
    0.07
    --------------------
    0.07
     Yours
    0.07
    豪华
    0.07
    Act Density 0.001%

    No Known Activations