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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bl
    -0.07
    _ment
    -0.07
    (rp
    -0.07
     dept
    -0.06
    牡
    -0.06
    Seriously
    -0.06
    RuntimeObject
    -0.06
     culprit
    -0.06
    OID
    -0.06
    Assoc
    -0.06
    POSITIVE LOGITS
    震惊
    0.07
    rose
    0.07
    ал
    0.07
     agreed
    0.07
     improves
    0.07
    thanks
    0.07
    includes
    0.07
     Quality
    0.07
    �
    0.07
    emploi
    0.07
    Act Density 0.001%

    No Known Activations