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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']");↵
    -0.06
    lém
    -0.06
    iene
    -0.06
    えた
    -0.06
     نوش
    -0.06
    _embed
    -0.06
    ohan
    -0.06
    รวจ
    -0.05
    жен
    -0.05
    ]↵
    -0.05
    POSITIVE LOGITS
    writers
    0.06
    克
    0.06
    -star
    0.06
     weaknesses
    0.06
    _ABC
    0.06
     contracted
    0.06
    Dec
    0.06
     CHILD
    0.06
     securities
    0.06
    INI
    0.06
    Act Density 0.000%

    No Known Activations