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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essa
    -0.07
     agosto
    -0.07
    加强对
    -0.07
     Virt
    -0.07
    勺
    -0.06
    cribing
    -0.06
     perpetrated
    -0.06
    .parts
    -0.06
     Verizon
    -0.06
     tod
    -0.06
    POSITIVE LOGITS
    (listener
    0.08
    ’)
    0.07
    库
    0.07
     barn
    0.07
     Championships
    0.07
     ראשי
    0.07
    贏
    0.07
    변
    0.07
     METHODS
    0.07
    ⏰
    0.07
    Act Density 0.001%

    No Known Activations