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
    Virtual
    -0.07
     seems
    -0.06
    prar
    -0.06
     glorious
    -0.06
    足
    -0.06
     MODEL
    -0.06
    Simulation
    -0.06
    уществ
    -0.06
     Seriously
    -0.05
    ोश
    -0.05
    POSITIVE LOGITS
    -inch
    0.07
    liable
    0.07
    %)
    0.07
     конкур
    0.07
    "',
    0.07
     '{}'
    0.07
    HF
    0.06
    ],'
    0.06
    .);↵
    0.06
    >";
    0.06
    Act Density 0.007%

    No Known Activations