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

    Neuronpedia

    INDEX
    Explanations

    promotional offer exclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FIL
    -0.07
    eken
    -0.06
    Reward
    -0.06
     fan
    -0.06
    �
    -0.06
     Ivan
    -0.06
    クション
    -0.06
    (QIcon
    -0.06
     enviar
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    jr
    0.08
    اصله
    0.07
    &r
    0.07
     ‪
    0.07
     resolving
    0.07
     powering
    0.07
    监
    0.06
    ="(
    0.06
    Dates
    0.06
    _Play
    0.06
    Act Density 0.003%

    No Known Activations