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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عملکرد
    -0.07
     nausea
    -0.07
    papers
    -0.06
    (loc
    -0.06
     Documents
    -0.06
    Yaw
    -0.06
     Нав
    -0.06
     венти
    -0.06
     Kot
    -0.06
    颜
    -0.06
    POSITIVE LOGITS
     Jess
    0.08
    Around
    0.08
    rd
    0.08
     third
    0.07
    ARDS
    0.07
    (boost
    0.07
    keywords
    0.07
    flix
    0.07
    TINGS
    0.07
     deceit
    0.07
    Act Density 0.006%

    No Known Activations