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

    Neuronpedia

    INDEX
    Explanations

    sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travels
    -0.08
     desen
    -0.08
     decl
    -0.08
    ங்கே
    -0.07
     descriptors
    -0.07
     الشخصية
    -0.07
     pertenece
    -0.07
     yourself
    -0.07
    alaya
    -0.07
     belongs
    -0.07
    POSITIVE LOGITS
    旗下
    0.11
     ತನ್ನ
    0.10
    员工
    0.10
     prides
    0.09
     motto
    0.09
     తమ
    0.09
     തന്റെ
    0.09
     employing
    0.09
     নিজেদের
    0.09
     grapple
    0.08
    Act Density 0.638%

    No Known Activations