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

    Neuronpedia

    INDEX
    Explanations

    host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staples
    -0.06
     CAM
    -0.06
    crud
    -0.06
    _ann
    -0.06
    _TRANS
    -0.06
     cris
    -0.05
    ेड
    -0.05
     लड
    -0.05
     aggravated
    -0.05
    adox
    -0.05
    POSITIVE LOGITS
     ovarian
    0.07
     guru
    0.07
     opportun
    0.07
    Host
    0.07
     Telegram
    0.06
    (link
    0.06
     overdue
    0.06
     jika
    0.06
     نوع
    0.06
    ตร
    0.06
    Act Density 0.014%

    No Known Activations