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

    Neuronpedia

    INDEX
    Explanations

    stronger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fore
    -0.08
     burgeoning
    -0.08
     freak
    -0.08
     thriving
    -0.08
    Dream
    -0.08
    -0.07
    戲
    -0.07
    Tutorial
    -0.07
     abr
    -0.07
     longevity
    -0.07
    POSITIVE LOGITS
     சொ
    0.08
     полу
    0.08
     ताक
    0.08
     Fortunately
    0.07
     veloc
    0.07
    偿
    0.07
    eless
    0.07
    /general
    0.07
     தாக்க
    0.07
    武
    0.07
    Act Density 0.002%
    No Known Activations