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
    ीं,
    -0.07
    (IP
    -0.07
     GIF
    -0.07
    ior
    -0.07
     temps
    -0.06
    린
    -0.06
     indirect
    -0.06
    ynos
    -0.06
     serviços
    -0.06
    ruit
    -0.06
    POSITIVE LOGITS
     existed
    0.07
    andalone
    0.06
    -tab
    0.06
    unbind
    0.06
    ै।↵↵
    0.06
    _attempt
    0.06
    jišť
    0.06
    раз
    0.06
     ))↵
    0.06
     cigarette
    0.06
    Act Density 0.068%

    No Known Activations