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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predetermined
    -0.07
    -analysis
    -0.07
     Confirm
    -0.07
    (vehicle
    -0.07
    -thirds
    -0.07
    まった
    -0.07
    	Message
    -0.07
    _REGION
    -0.06
     duke
    -0.06
     discontent
    -0.06
    POSITIVE LOGITS
    _UnityEngine
    0.06
    복지
    0.06
     dos
    0.06
     weekends
    0.06
     MUT
    0.06
    .Setter
    0.05
     Toilet
    0.05
     tweak
    0.05
     FDA
    0.05
    urger
    0.05
    Act Density 0.022%

    No Known Activations