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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hard
    -0.07
     summed
    -0.06
     Inject
    -0.06
    .Core
    -0.06
     eve
    -0.06
    ektedir
    -0.06
    ();)
    -0.06
     Lords
    -0.06
     disconnect
    -0.06
    *((
    -0.06
    POSITIVE LOGITS
    �
    0.07
     دل
    0.07
     تحصیل
    0.07
     persone
    0.06
    cola
    0.06
     Portug
    0.06
    essoa
    0.06
     предел
    0.06
     Bailey
    0.06
    cribes
    0.06
    Act Density 0.001%

    No Known Activations