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

    Neuronpedia

    INDEX
    Explanations

    pre-game/race activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aim
    -0.07
    注重
    -0.07
    Arial
    -0.07
     NEC
    -0.07
    觉悟
    -0.07
     coat
    -0.07
    ición
    -0.06
    iid
    -0.06
    oles
    -0.06
     SSA
    -0.06
    POSITIVE LOGITS
    Shipping
    0.08
    agnostics
    0.07
     данном
    0.07
     Changed
    0.07
     всех
    0.07
    稳定性
    0.07
     том
    0.07
    depend
    0.07
     amazing
    0.07
    _verify
    0.06
    Act Density 0.047%

    No Known Activations