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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    联
    -0.08
    CADE
    -0.07
    -0.06
    Tanggal
    -0.06
     CAB
    -0.06
    Swipe
    -0.06
     круп
    -0.06
    婷
    -0.06
     breve
    -0.06
    FO
    -0.06
    POSITIVE LOGITS
     excellent
    0.06
     initialise
    0.06
    _decay
    0.06
    ahun
    0.06
    imestone
    0.06
    enheim
    0.06
    760
    0.06
    其他
    0.06
    ，以
    0.06
    igs
    0.06
    Act Density 0.000%

    No Known Activations