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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ø
    -0.07
     �
    -0.07
     أو
    -0.07
     AJ
    -0.06
    _Char
    -0.06
    _soft
    -0.06
    _Al
    -0.06
     FM
    -0.06
    naissance
    -0.06
    ;!
    -0.06
    POSITIVE LOGITS
    .each
    0.07
    osterone
    0.07
    (anchor
    0.07
    moz
    0.06
    \"></
    0.06
     ;
↵
↵
    0.06
    ]‏
    0.06
     leaked
    0.06
    .ReactNode
    0.06
     KeyboardInterrupt
    0.06
    Act Density 0.003%

    No Known Activations