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

    Neuronpedia

    INDEX
    Explanations

    oj/Woj/Wow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %}↵
    -0.07
    issors
    -0.06
     seized
    -0.06
     Hudson
    -0.06
    ambre
    -0.06
    428
    -0.06
     interaction
    -0.06
    ))
↵
↵
    -0.06
    }.{
    -0.06
    -desc
    -0.06
    POSITIVE LOGITS
    .od
    0.08
     Woo
    0.08
    -night
    0.07
    печ
    0.07
    운
    0.07
    _states
    0.07
    nie
    0.07
    スコ
    0.07
    stalk
    0.07
    �ng
    0.07
    Act Density 0.005%

    No Known Activations