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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uLocal
    -0.07
     lor
    -0.07
    illard
    -0.07
    汕
    -0.07
    ror
    -0.07
    _prime
    -0.06
    *'
    -0.06
    ɧ
    -0.06
     toplantı
    -0.06
    ſt
    -0.06
    POSITIVE LOGITS
    Nom
    0.08
    "↵
    0.08
    ";↵
    0.08
    	defer
    0.08
    更能
    0.07
    )"↵
    0.07
    )",↵
    0.07
     cher
    0.07
     '}';↵
    0.07
    .";↵
    0.07
    Act Density 0.001%

    No Known Activations