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

    Neuronpedia

    INDEX
    Explanations

    hovering near or around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hierarchies
    0.39
    సం
    0.38
     hierarchy
    0.36
    經過
    0.36
     tenfold
    0.35
     마련
    0.34
     kalite
    0.34
    0.34
    连接
    0.34
    经过
    0.34
    POSITIVE LOGITS
     close
    1.14
     near
    1.09
     близь
    1.02
    close
    1.00
     slightly
    1.00
    near
    0.94
     близ
    0.93
     hovering
    0.93
     marginally
    0.92
     around
    0.88
    Act Density 0.080%

    No Known Activations