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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "])
↵
    -0.07
     предел
    -0.07
     بین
    -0.07
     Παν
    -0.07
     compart
    -0.07
     θε
    -0.07
     paddingRight
    -0.06
    獎
    -0.06
     suma
    -0.06
    Priv
    -0.06
    POSITIVE LOGITS
    ered
    0.06
    \system
    0.06
     IPA
    0.06
    OE
    0.06
    虫
    0.06
     Duplicate
    0.06
     dominates
    0.06
    iang
    0.05
    erox
    0.05
    reten
    0.05
    Act Density 0.011%

    No Known Activations