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

    Neuronpedia

    INDEX
    Explanations

    and/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     które
    -0.08
    LS
    -0.07
    -football
    -0.07
     Floors
    -0.07
    -inc
    -0.06
     şekil
    -0.06
     Contribution
    -0.06
    _responses
    -0.06
     chiefs
    -0.06
     principals
    -0.06
    POSITIVE LOGITS
     Sabb
    0.07
     pien
    0.06
    isure
    0.06
     خانم
    0.06
     ">↵
    0.06
     Ethan
    0.06
    _ATTACHMENT
    0.06
    케
    0.06
     pigeon
    0.05
    ारन
    0.05
    Act Density 0.420%

    No Known Activations