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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sha
    -0.06
    _nb
    -0.06
     Δη
    -0.06
     overriding
    -0.06
    нюю
    -0.06
    Networking
    -0.06
     stupidity
    -0.06
     gamle
    -0.06
     flushing
    -0.05
     ダ
    -0.05
    POSITIVE LOGITS
     effortless
    0.08
     hallway
    0.07
     모두
    0.07
     orgán
    0.06
    umi
    0.06
    ecome
    0.06
     electrodes
    0.06
     businesses
    0.06
    零
    0.06
    verter
    0.06
    Act Density 0.001%

    No Known Activations