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

    Neuronpedia

    INDEX
    Explanations

    -schema

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pans
    -0.07
     från
    -0.07
    (amount
    -0.07
     Marlins
    -0.06
    Mountain
    -0.06
     workload
    -0.06
    (l
    -0.06
    .Loader
    -0.06
     roaring
    -0.06
    谓
    -0.06
    POSITIVE LOGITS
     väl
    0.07
     форме
    0.07
    (dy
    0.07
    /screen
    0.06
    initialized
    0.06
     lorsque
    0.06
    ;b
    0.06
    SelectionMode
    0.06
     ^{°}
    0.06
     paramet
    0.06
    Act Density 0.002%

    No Known Activations