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

    Neuronpedia

    INDEX
    Explanations

    yes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LK
    -0.07
     Club
    -0.07
    342
    -0.07
     Protect
    -0.07
     Stuff
    -0.07
    _LOAD
    -0.06
     CLUB
    -0.06
     الذي
    -0.06
     Shadow
    -0.06
    程序
    -0.06
    POSITIVE LOGITS
     Yes
    0.16
    Yes
    0.14
    "Yes
    0.13
     yes
    0.13
     YES
    0.12
    “Yes
    0.12
    "Yeah
    0.11
     yeah
    0.10
    _yes
    0.09
    YES
    0.09
    Act Density 0.035%

    No Known Activations