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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TestCase
    -0.08
     Chairs
    -0.07
    atom
    -0.07
     nz
    -0.06
    裏
    -0.06
     dzieci
    -0.06
    .pt
    -0.06
     لل
    -0.06
    คอม
    -0.06
    ์ของ
    -0.06
    POSITIVE LOGITS
    _Settings
    0.07
    swift
    0.07
    gium
    0.06
    RID
    0.06
    USED
    0.06
    });
↵
    0.06
    hub
    0.06
     appointed
    0.06
    oldown
    0.06
    _LENGTH
    0.06
    Act Density 0.003%

    No Known Activations