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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iconic
    -0.07
     sitios
    -0.07
     Cold
    -0.06
    .impl
    -0.06
     cues
    -0.06
     legally
    -0.06
     losers
    -0.06
     formal
    -0.06
    :UIAlert
    -0.06
    猴
    -0.06
    POSITIVE LOGITS
     Arkansas
    0.07
    Workflow
    0.07
     общ
    0.06
    能看出
    0.06
    ivation
    0.06
    iffany
    0.06
    频道
    0.06
     Judiciary
    0.06
    Pref
    0.06
    听得
    0.06
    Act Density 0.004%

    No Known Activations