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

    Neuronpedia

    INDEX
    Explanations

    making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jame
    -0.07
    ynet
    -0.07
     Gabri
    -0.06
    _ex
    -0.06
    抜
    -0.06
     lenders
    -0.06
     gros
    -0.06
    _dup
    -0.06
    มาก
    -0.06
     Deputy
    -0.06
    POSITIVE LOGITS
    )];
↵
    0.07
    _SIMPLE
    0.07
    .expires
    0.06
     ~~
    0.06
    (png
    0.06
    LE
    0.06
    .setUser
    0.06
    lear
    0.06
    }")↵
    0.06
    })
    0.06
    Act Density 0.062%

    No Known Activations