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

    Neuronpedia

    INDEX
    Explanations

    body horror and auto-ethnographic entry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }},
    0.48
     colourful
    0.47
     berg
    0.46
     eloquent
    0.46
     hampers
    0.46
    lush
    0.46
     gowns
    0.45
    ब्स
    0.44
    嬠
    0.44
    édrale
    0.44
    POSITIVE LOGITS
    Grant
    0.52
    Generate
    0.52
    Research
    0.51
    Baseline
    0.50
    Student
    0.50
    Prepare
    0.49
    Dr
    0.48
    Nexus
    0.48
    Events
    0.48
    Calcul
    0.48
    Act Density 0.001%

    No Known Activations