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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decree
    -0.07
     �
    -0.07
    BMI
    -0.06
     vocals
    -0.06
     msm
    -0.06
    ertation
    -0.06
    	not
    -0.06
     Insert
    -0.06
     οπο
    -0.06
    ували
    -0.06
    POSITIVE LOGITS
     Assault
    0.07
    	flash
    0.07
    ((-
    0.06
     Target
    0.06
    ίγ
    0.06
     target
    0.06
     Intersection
    0.06
     assault
    0.06
    ":"","
    0.06
    LBL
    0.06
    Act Density 0.047%

    No Known Activations