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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unfavorable
    -0.08
    ол
    -0.07
    _MOBILE
    -0.07
    Poll
    -0.07
    egree
    -0.07
    PRO
    -0.07
     Internet
    -0.07
     favourable
    -0.07
     kol
    -0.06
    .Tags
    -0.06
    POSITIVE LOGITS
     gone
    0.07
     �
    0.06
     تنها
    0.06
     ít
    0.06
     synd
    0.06
    _yes
    0.06
    _vk
    0.06
    )를
    0.06
     इसस
    0.06
     �
    0.06
    Act Density 0.005%

    No Known Activations