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

    Neuronpedia

    INDEX
    Explanations

    20*

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hti
    -0.07
    achine
    -0.06
    iset
    -0.06
    _length
    -0.06
    Depth
    -0.06
    世紀
    -0.06
    огда
    -0.06
    setWidth
    -0.06
     женщин
    -0.06
     verbs
    -0.06
    POSITIVE LOGITS
     Agricult
    0.07
    /o
    0.07
    REFERENCE
    0.07
    (Symbol
    0.06
    Um
    0.06
    .§
    0.06
    CommandEvent
    0.06
     :+:
    0.06
    )
↵
↵
↵
    0.06
     envoy
    0.06
    Act Density 0.006%

    No Known Activations