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

    Neuronpedia

    INDEX
    Explanations

    fix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Miami
    -0.07
    jdbc
    -0.06
     attacked
    -0.06
     attacking
    -0.06
    091
    -0.06
    ='{$
    -0.06
    \modules
    -0.06
     McGregor
    -0.05
    raki
    -0.05
     goalkeeper
    -0.05
    POSITIVE LOGITS
    -host
    0.08
     б
    0.07
    ]';↵
    0.07
    _BUILD
    0.06
    **(
    0.06
    ">↵↵
    0.06
    .EventHandler
    0.06
     nex
    0.06
    "/>↵↵
    0.06
     IMessage
    0.06
    Act Density 0.020%

    No Known Activations