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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _alert
    -0.07
     discs
    -0.07
    iska
    -0.07
    ób
    -0.07
     packed
    -0.07
     alerts
    -0.07
    ovky
    -0.06
     ayant
    -0.06
    .find
    -0.06
    -card
    -0.06
    POSITIVE LOGITS
     IDR
    0.07
     конкрет
    0.06
    _env
    0.06
    (environment
    0.06
     {}:
    0.06
    FLOW
    0.06
    PathComponent
    0.06
     그것
    0.06
     �
    0.06
     loser
    0.06
    Act Density 0.011%

    No Known Activations