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

    Neuronpedia

    INDEX
    Explanations

    to verb phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ема
    0.51
    িনে
    0.38
     strang
    0.38
    aire
    0.36
     hoisting
    0.36
     høj
    0.36
    zecz
    0.36
     PRINT
    0.35
     emojis
    0.35
     sii
    0.35
    POSITIVE LOGITS
     Copies
    0.44
    Copies
    0.41
     Institutional
    0.40
     قنات
    0.40
     இதன்
    0.39
    Duplicate
    0.39
     QUEEN
    0.38
     அன்பு
    0.38
    ConnectionType
    0.38
    殳
    0.37
    Act Density 0.001%

    No Known Activations