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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |
    -0.08
    -
    -0.08
    (?
    -0.08
    ी-
    -0.07
     Bangalore
    -0.07
    …
    -0.07
    ***
    -0.07
     तरफ
    -0.07
     Arab
    -0.07
    u
    -0.07
    POSITIVE LOGITS
     D
    0.07
     احساس
    0.07
     G
    0.07
     S
    0.07
     und
    0.07
    \S
    0.06
    _nm
    0.06
     R
    0.06
     kW
    0.06
     M
    0.06
    Act Density 0.015%

    No Known Activations