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

    Neuronpedia

    INDEX
    Explanations

    pieces, resource, properties, rebellion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    贓
    0.48
     nitidus
    0.48
    ForEach
    0.48
     prostřed
    0.47
     portal
    0.47
     banca
    0.46
     laurels
    0.46
    ForThe
    0.46
     monto
    0.46
     gai
    0.46
    POSITIVE LOGITS
     Discussion
    0.48
     Air
    0.46
     ANGELES
    0.45
    עות
    0.45
     Hern
    0.45
     Earrings
    0.44
    wert
    0.44
     Bung
    0.44
    毽
    0.44
     फुटबल
    0.43
    Act Density 0.000%

    No Known Activations