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

    Neuronpedia

    INDEX
    Explanations

    ing, briefing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orro
    -0.07
    (z
    -0.07
    ・━・━
    -0.07
     DNA
    -0.07
    шки
    -0.06
    剣
    -0.06
    gun
    -0.06
    IPC
    -0.06
    猫
    -0.06
    358
    -0.06
    POSITIVE LOGITS
     briefing
    0.12
     briefed
    0.10
    _story
    0.07
     presentation
    0.07
     presentations
    0.07
     Brief
    0.06
    /me
    0.06
     tutorials
    0.06
    bies
    0.06
     impressed
    0.06
    Act Density 0.003%

    No Known Activations