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

    Neuronpedia

    INDEX
    Explanations

    being trapped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spilling
    0.38
     summing
    0.36
     witch
    0.35
     idea
    0.34
     consolation
    0.34
     useDispatch
    0.34
     dealing
    0.33
     이야
    0.33
     stirring
    0.32
     molding
    0.32
    POSITIVE LOGITS
     trapped
    0.91
     traps
    0.86
    Trap
    0.80
     Trap
    0.79
     trap
    0.79
    trap
    0.77
    陷
    0.68
     trapping
    0.67
     entrap
    0.54
     captive
    0.51
    Act Density 0.000%

    No Known Activations