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

    Neuronpedia

    INDEX
    Explanations

    Production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     measurable
    -0.08
    蠼
    -0.07
    _gen
    -0.07
    сколько
    -0.07
    SETTING
    -0.07
    [,
    -0.07
    随手
    -0.07
    ╴
    -0.07
    Segments
    -0.06
    Cl
    -0.06
    POSITIVE LOGITS
    .Entry
    0.08
    :")↵
    0.07
    ᄌ
    0.07
    (parameters
    0.07
    ÂN
    0.07
     WhatsApp
    0.07
     freq
    0.07
     Dawn
    0.07
    ROOM
    0.07
    -eight
    0.07
    Act Density 0.012%

    No Known Activations