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

    Neuronpedia

    INDEX
    Explanations

    listings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TOP
    -0.07
    측
    -0.06
    PRESENT
    -0.06
     regularization
    -0.06
    }=
    -0.06
    .central
    -0.06
    caffold
    -0.06
    _For
    -0.06
     scaffold
    -0.06
    stown
    -0.06
    POSITIVE LOGITS
     vue
    0.07
     =================================
    0.07
     ignored
    0.06
     popover
    0.06
    цуз
    0.06
     สถาน
    0.06
    /********************************
    0.06
    Enum
    0.06
     因
    0.06
     cheeses
    0.06
    Act Density 0.004%

    No Known Activations