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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Name
    -0.07
    ":"",↵
    -0.07
     expansions
    -0.07
     Plans
    -0.07
    Vars
    -0.07
     ignore
    -0.07
    _DOMAIN
    -0.07
    _INLINE
    -0.06
    _LD
    -0.06
     concealed
    -0.06
    POSITIVE LOGITS
    없
    0.06
    (filter
    0.06
    atie
    0.06
     timely
    0.06
    죽
    0.06
    authorize
    0.06
     Weg
    0.06
    Administration
    0.05
    (Service
    0.05
    ▲
    0.05
    Act Density 0.016%

    No Known Activations