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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    曰
    -0.07
    직
    -0.06
     fool
    -0.06
    @",
    -0.06
    	Port
    -0.06
     �
    -0.06
    áng
    -0.06
     pel
    -0.06
    .parse
    -0.06
    baar
    -0.06
    POSITIVE LOGITS
     پایین
    0.07
     تازه
    0.07
    ]){↵
    0.06
    (HaveOccurred
    0.06
     договор
    0.06
     etc
    0.06
    IMIZE
    0.06
    _emails
    0.06
    ruptcy
    0.06
     SHA
    0.06
    Act Density 0.003%

    No Known Activations