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

    Neuronpedia

    INDEX
    Explanations

    Positive, exclamatory blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    公积
    -0.07
    (strtolower
    -0.06
    Recovered
    -0.06
    _approved
    -0.06
    具备
    -0.06
    ➮
    -0.06
     aviation
    -0.06
    藝
    -0.06
     preced
    -0.06
    力争
    -0.06
    POSITIVE LOGITS
    @a
    0.07
    fq
    0.07
     faithfully
    0.07
    więks
    0.07
    连
    0.07
    抗震
    0.06
     packets
    0.06
    第三代
    0.06
     immersive
    0.06
     buttonWithType
    0.06
    Act Density 0.028%

    No Known Activations