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

    Neuronpedia

    INDEX
    Explanations

    prefixes and suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    599
    -0.06
     IconData
    -0.06
    572
    -0.06
    .false
    -0.06
    	AT
    -0.06
    799
    -0.06
     徒
    -0.06
    658
    -0.05
    ocê
    -0.05
    ra
    -0.05
    POSITIVE LOGITS
     khối
    0.08
    ايش
    0.07
    alian
    0.07
    칭
    0.07
     ordered
    0.07
     signatures
    0.07
     advertised
    0.07
     booked
    0.06
    غل
    0.06
    position
    0.06
    Act Density 0.000%

    No Known Activations