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

    Neuronpedia

    INDEX
    Explanations

    But

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -java
    -0.07
    _F
    -0.07
     numRows
    -0.06
    Blocks
    -0.06
     Aviation
    -0.06
     -->↵↵
    -0.06
     slu
    -0.06
    .div
    -0.06
    \ActiveForm
    -0.06
    (Order
    -0.06
    POSITIVE LOGITS
     NOTES
    0.07
     состояния
    0.06
    imento
    0.06
    _RANGE
    0.06
     outgoing
    0.06
    ращения
    0.06
     }}}
    0.06
     Blanco
    0.06
    ounce
    0.06
     зміст
    0.06
    Act Density 0.050%

    No Known Activations