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

    Neuronpedia

    INDEX
    Explanations

    Non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worce
    -0.07
     restitution
    -0.07
    ilde
    -0.07
    meter
    -0.06
     เว
    -0.06
     europe
    -0.06
    />
↵
    -0.06
     Vincent
    -0.06
     Hermes
    -0.06
    vere
    -0.06
    POSITIVE LOGITS
    AJ
    0.08
     zvlá
    0.08
    aj
    0.07
    -<?
    0.06
    ai
    0.06
     dáng
    0.06
    Len
    0.06
     Frames
    0.06
     Championship
    0.06
     ramifications
    0.06
    Act Density 0.017%

    No Known Activations