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

    Neuronpedia

    INDEX
    Explanations

    capability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objects
    -0.07
     examination
    -0.07
     элем
    -0.07
     adm
    -0.06
     fiz
    -0.06
     subjects
    -0.06
     exam
    -0.06
    -tw
    -0.06
    :number
    -0.06
     bulb
    -0.06
    POSITIVE LOGITS
     capability
    0.10
     nightmare
    0.09
     Capability
    0.08
     chuyến
    0.07
     capabilities
    0.07
    Caps
    0.07
    ิทธ
    0.07
     benchmark
    0.07
     avatar
    0.07
    ourcing
    0.07
    Act Density 0.007%

    No Known Activations