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

    Neuronpedia

    INDEX
    Explanations

    cyc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    材
    -0.07
     MAN
    -0.07
     Pron
    -0.07
     Περ
    -0.07
     nors
    -0.07
    _dir
    -0.06
     Ten
    -0.06
    /man
    -0.06
    앤
    -0.06
    อร
    -0.06
    POSITIVE LOGITS
     cyc
    0.12
     Cyc
    0.10
    ΟΚ
    0.08
     battleground
    0.07
     \''
    0.07
     Cycle
    0.07
     progress
    0.07
     watchdog
    0.07
     deep
    0.07
    lok
    0.07
    Act Density 0.005%

    No Known Activations