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

    Neuronpedia

    INDEX
    Explanations

    bill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umped
    -0.07
     stump
    -0.07
    ꦏ
    -0.07
     admissions
    -0.07
    钢结构
    -0.07
    ㌃
    -0.07
    Textures
    -0.07
    ม
    -0.07
     wealthiest
    -0.07
    侵占
    -0.07
    POSITIVE LOGITS
    How
    0.07
    idian
    0.07
     Cheryl
    0.07
    SHARE
    0.07
    长安
    0.06
    ?↵↵↵↵↵↵
    0.06
     Dim
    0.06
     sonrasında
    0.06
     legislation
    0.06
    >'
    0.06
    Act Density 0.015%

    No Known Activations