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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chad
    -0.07
    提供
    -0.06
    Dick
    -0.06
    _pid
    -0.06
    珍
    -0.06
    withdraw
    -0.06
    طة
    -0.06
     raid
    -0.06
     cruis
    -0.06
    walker
    -0.06
    POSITIVE LOGITS
    .Topic
    0.07
    ･･
    0.07
    evším
    0.07
     �
    0.06
    .high
    0.06
     Json
    0.06
     Paginator
    0.06
    	category
    0.06
     Strand
    0.06
     ->↵
    0.06
    Act Density 0.021%

    No Known Activations