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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     モ
    -0.07
     dak
    -0.06
    och
    -0.06
     Mn
    -0.06
     öne
    -0.06
     정확
    -0.06
    -r
    -0.06
     missions
    -0.06
     Централь
    -0.06
     han
    -0.06
    POSITIVE LOGITS
     doubted
    0.06
    SQLException
    0.06
     tutorial
    0.06
     WITHOUT
    0.06
    ］
    0.06
     adorn
    0.06
    ()];↵
    0.06
    .World
    0.06
     outs
    0.06
    setDescription
    0.06
    Act Density 0.002%

    No Known Activations