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

    Neuronpedia

    INDEX
    Explanations

    keep updated/synchronized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    בינו
    -0.07
     fork
    -0.07
     tent
    -0.07
     xmm
    -0.07
     inputData
    -0.07
     nah
    -0.07
    pow
    -0.07
     PACKET
    -0.06
    inton
    -0.06
    (pass
    -0.06
    POSITIVE LOGITS
    stantial
    0.07
     Conclusion
    0.07
     claims
    0.07
    덫
    0.07
     발견
    0.07
    :Add
    0.06
    깣
    0.06
     Evaluation
    0.06
     Amir
    0.06
    >.↵
    0.06
    Act Density 0.047%

    No Known Activations