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

    Neuronpedia

    INDEX
    Explanations

    Open parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     ]↵↵↵
    -0.07
    _attached
    -0.07
    .adj
    -0.07
     מצווה
    -0.07
    🦋
    -0.07
     Featured
    -0.07
    ']↵↵↵
    -0.07
     "'.$
    -0.07
    ">↵↵↵
    -0.07
    POSITIVE LOGITS
    -syntax
    0.08
    劑
    0.08
     problema
    0.07
     heterosexual
    0.07
    Allowed
    0.07
    icy
    0.07
     зани
    0.07
    剂
    0.07
    constexpr
    0.06
    imony
    0.06
    Act Density 0.009%

    No Known Activations