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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	retval
    -0.08
     medium
    -0.07
     enemy
    -0.07
    Rp
    -0.07
    -policy
    -0.06
    "#
    -0.06
     ivory
    -0.06
     LLP
    -0.06
    оруж
    -0.06
     entrev
    -0.06
    POSITIVE LOGITS
     прок
    0.07
     onComplete
    0.07
    ｡
    0.06
    ItemCount
    0.06
    Installed
    0.06
     ژوئ
    0.06
     ima
    0.06
     Christopher
    0.06
    _toolbar
    0.06
    ――――
    0.06
    Act Density 0.004%

    No Known Activations