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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kj
    -0.07
     Metal
    -0.07
    .Event
    -0.07
    �
    -0.07
    .readFile
    -0.06
     wt
    -0.06
     #@
    -0.06
     Armstrong
    -0.06
     exceptional
    -0.06
     mužů
    -0.06
    POSITIVE LOGITS
    formerly
    0.06
    =password
    0.06
     darauf
    0.06
     tonumber
    0.06
     Prescott
    0.06
    /ar
    0.06
    \Extension
    0.06
    Fee
    0.06
     podcasts
    0.06
    ;left
    0.05
    Act Density 0.004%

    No Known Activations