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

    Neuronpedia

    INDEX
    Explanations

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Olympus
    -0.07
     vanished
    -0.07
     Pa
    -0.06
    ulace
    -0.06
    chip
    -0.06
     interactions
    -0.06
    ління
    -0.06
     plur
    -0.06
     losses
    -0.06
     violated
    -0.06
    POSITIVE LOGITS
     उसक
    0.07
    (env
    0.07
     Iraq
    0.06
    beiten
    0.06
     Demonstr
    0.06
    帰
    0.06
     العراق
    0.06
     quaint
    0.06
    (host
    0.06
    (arg
    0.06
    Act Density 0.007%

    No Known Activations