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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -place
    -0.07
     قائمة
    -0.07
     Jaguar
    -0.06
     Rek
    -0.06
     Put
    -0.06
    -taking
    -0.06
    /car
    -0.06
    xlsx
    -0.06
    cpu
    -0.06
    âte
    -0.06
    POSITIVE LOGITS
    		↵		↵		↵
    0.07
     love
    0.07
    基于
    0.06
     intrigue
    0.06
    ManagedObject
    0.06
    dfs
    0.06
     도
    0.06
    ẻ
    0.06
     jsou
    0.06
    ALLY
    0.06
    Act Density 0.043%

    No Known Activations