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

    Neuronpedia

    INDEX
    Explanations

    rot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dříve
    -0.07
     interoper
    -0.07
     наприклад
    -0.07
     хими
    -0.07
    前に
    -0.07
     infinit
    -0.07
     Undefined
    -0.07
     ant
    -0.06
     situace
    -0.06
    ethnic
    -0.06
    POSITIVE LOGITS
    _EMAIL
    0.06
    modo
    0.06
     Vel
    0.06
     밀
    0.06
    ).</
    0.06
    Strict
    0.06
    	Iterator
    0.06
    	params
    0.06
     Matters
    0.06
     Avengers
    0.05
    Act Density 0.010%

    No Known Activations