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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ranked
    -0.07
     başar
    -0.07
    Công
    -0.07
    "github
    -0.06
    _mock
    -0.06
     sarcast
    -0.06
    Atl
    -0.06
    위를
    -0.06
    ozřejmě
    -0.06
    matchCondition
    -0.06
    POSITIVE LOGITS
    semble
    0.06
     construed
    0.06
    \Web
    0.06
     SMALL
    0.06
     Oct
    0.06
     стари
    0.06
     heating
    0.06
    _Admin
    0.06
     을
    0.06
     Orbit
    0.05
    Act Density 0.013%

    No Known Activations