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

    Neuronpedia

    INDEX
    Explanations

    travel plans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gamma
    -0.07
     door
    -0.07
    notes
    -0.07
     experts
    -0.07
    Who
    -0.07
    warm
    -0.06
     navigate
    -0.06
    aches
    -0.06
    aktion
    -0.06
    hill
    -0.06
    POSITIVE LOGITS
    .assertIn
    0.07
    -prom
    0.07
     축
    0.07
     Himal
    0.07
     인천
    0.07
    /max
    0.06
     Minneapolis
    0.06
    روف
    0.06
     getData
    0.06
     newState
    0.06
    Act Density 0.015%

    No Known Activations