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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rush
    -0.07
     geri
    -0.07
    _CHARS
    -0.07
    \HttpFoundation
    -0.07
    stoupil
    -0.07
     Istanbul
    -0.06
     questi
    -0.06
    .elapsed
    -0.06
     yurt
    -0.06
     totaling
    -0.06
    POSITIVE LOGITS
     س
    0.06
     nature
    0.06
    ข
    0.06
     him
    0.06
     ·
    0.06
    أس
    0.06
    設
    0.06
    _PRO
    0.06
    орон
    0.06
    光
    0.06
    Act Density 0.035%

    No Known Activations