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

    Neuronpedia

    INDEX
    Explanations

    MD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芙
    -0.08
     맥
    -0.06
    acak
    -0.06
    (host
    -0.06
     �
    -0.06
     Philly
    -0.06
     chatte
    -0.06
     bryster
    -0.06
    olf
    -0.06
     pillars
    -0.06
    POSITIVE LOGITS
     Afghanistan
    0.07
     друг
    0.06
     backyard
    0.06
    _required
    0.06
     numerous
    0.06
     grief
    0.06
     economically
    0.06
     Accounting
    0.06
     ';'
    0.06
     accounting
    0.06
    Act Density 0.004%

    No Known Activations