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

    Neuronpedia

    INDEX
    Explanations

    ml

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eid
    -0.07
    ційних
    -0.07
    岛
    -0.07
     Actors
    -0.06
     Emil
    -0.06
     où
    -0.06
     jihad
    -0.06
     soudu
    -0.06
    端
    -0.06
    Term
    -0.06
    POSITIVE LOGITS
     mL
    0.07
    Deferred
    0.07
    stddef
    0.07
    lr
    0.07
     litre
    0.06
    }<
    0.06
     gallons
    0.06
    (pixel
    0.06
    �
    0.06
     %
    0.06
    Act Density 0.017%

    No Known Activations