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

    Neuronpedia

    INDEX
    Explanations

    months and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شیع
    0.35
     матч
    0.35
     misinformation
    0.34
     }^{-
    0.34
     enemigo
    0.33
    contacto
    0.32
    涔
    0.32
     Mỗi
    0.31
    Neigh
    0.31
     semelhante
    0.31
    POSITIVE LOGITS
    途
    0.35
     inlet
    0.35
    成り
    0.35
    İK
    0.34
     July
    0.34
    July
    0.33
     july
    0.31
     december
    0.31
     venture
    0.31
     outlet
    0.31
    Act Density 0.002%

    No Known Activations