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

    Neuronpedia

    INDEX
    Explanations

    Code/Scientific snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    噪音
    -0.07
    エネ
    -0.07
    醇
    -0.07
    _annotations
    -0.07
    iron
    -0.06
    getOption
    -0.06
    _fore
    -0.06
     forth
    -0.06
     terrain
    -0.06
    gn
    -0.06
    POSITIVE LOGITS
     FormsModule
    0.08
    cctor
    0.08
     تقوم
    0.07
    }";↵
    0.07
     صال
    0.07
    '));
↵
    0.07
    ＊
    0.07
     /↵
    0.07
    >";
    0.06
    };↵
    0.06
    Act Density 0.037%

    No Known Activations