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

    Neuronpedia

    INDEX
    Explanations

    medical, scientific contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     earliest
    -0.07
    -resolution
    -0.07
    《
    -0.06
     trained
    -0.06
    回暖
    -0.06
    فح
    -0.06
    倡导
    -0.06
     rejecting
    -0.06
    根据
    -0.06
     valores
    -0.06
    POSITIVE LOGITS
    Tab
    0.07
    Ø
    0.07
    不然
    0.07
     Omaha
    0.07
    _changes
    0.07
    ��이
    0.07
    Tel
    0.07
     Sab
    0.07
    ri
    0.06
    Communication
    0.06
    Act Density 0.346%

    No Known Activations